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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _oauth
    -0.07
    _get
    -0.06
    Official
    -0.06
     sparing
    -0.06
    ortic
    -0.06
    Forgery
    -0.06
    -0.06
     ceremon
    -0.06
    og
    -0.06
    iren
    -0.06
    POSITIVE LOGITS
    γή
    0.07
    標
    0.07
     TLabel
    0.07
    _NOTE
    0.06
     MESSAGE
    0.06
    yses
    0.06
    medicine
    0.06
     انتخابات
    0.06
     Gin
    0.06
    VAS
    0.06
    Act Density 0.099%

    No Known Activations