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

    Neuronpedia

    INDEX
    Explanations

    4 tweet, 4 GPT-4

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kavram
    0.29
     ‘’
    0.28
    "+"
    0.28
     lParam
    0.28
    abilités
    0.28
    راتيج
    0.28
    的概念
    0.28
     Variability
    0.28
    İŞ
    0.28
    Personality
    0.27
    POSITIVE LOGITS
     thee
    0.41
     thei
    0.40
    anwhile
    0.38
    cludes
    0.37
    cluded
    0.37
     други
    0.36
    the
    0.36
    those
    0.35
    cluding
    0.35
     thine
    0.35
    Act Density 0.021%

    No Known Activations