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

    Neuronpedia

    INDEX
    Explanations

    des

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cunt
    -0.06
     runner
    -0.06
    _DRAW
    -0.06
     Helping
    -0.06
     paren
    -0.06
    Ré
    -0.06
    man
    -0.06
     Cry
    -0.06
    acre
    -0.06
     parser
    -0.06
    POSITIVE LOGITS
     Ziel
    0.07
    NTSTATUS
    0.07
    ,status
    0.06
    .spinner
    0.06
    .sa
    0.06
    付け
    0.06
    訓
    0.06
    ++++++++++++++++
    0.06
    .AUTH
    0.06
    _APPEND
    0.06
    Act Density 0.018%

    No Known Activations