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

    Neuronpedia

    INDEX
    Explanations

    positive affirmations and recovery-related terms

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

    OK and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     European
    -0.33
     Star
    -0.32
     style
    -0.32
     format
    -0.31
     a
    -0.31
     EU
    -0.30
     flag
    -0.30
     des
    -0.30
     craft
    -0.30
     legacy
    -0.29
    POSITIVE LOGITS
    StoryboardSegue
    0.81
    ChildScrollView
    0.79
    JspWriter
    0.73
     zdrow
    0.69
    FunctionFlags
    0.69
    AsUp
    0.68
     Мексичка
    0.66
     Taktlose
    0.65
     snippetHide
    0.63
    ArrowToggle
    0.63
    Act Density 0.028%

    No Known Activations