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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     marzo
    -0.07
    	vertices
    -0.07
    最受
    -0.07
    ighbours
    -0.07
     referees
    -0.07
     subpoena
    -0.06
    ete
    -0.06
    تصر
    -0.06
    开局
    -0.06
     sounded
    -0.06
    POSITIVE LOGITS
    _MALLOC
    0.06
    个性化
    0.06
     Access
    0.06
    CurrentValue
    0.06
    PushButton
    0.06
    стой
    0.06
    科學
    0.06
    .iv
    0.06
     pobl
    0.06
    防御
    0.06
    Act Density 0.000%

    No Known Activations