Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    terms related to decision-making processes and operations in organizational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Unnecessary or avoidable actions

    np_acts-logits-general · gemini-2.0-flash

    unnecessary things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+#
    -0.82
    rrggbb
    -0.69
     Савезне
    -0.68
    Hentet
    -0.68
     Мексичка
    -0.66
     intptr
    -0.66
     oprot
    -0.65
     تضيفلها
    -0.64
    
    -0.63
     通販
    -0.62
    POSITIVE LOGITS
     unnecessary
    1.72
     unnecessarily
    1.49
     inneces
    1.47
     needlessly
    1.27
     avoidable
    1.06
     needless
    0.98
     inuti
    0.97
     inutile
    0.90
     unwarranted
    0.88
     superfluous
    0.85
    Act Density 0.372%

    No Known Activations