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

    Neuronpedia

    INDEX
    Explanations

    conditional statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Protestant
    -0.06
    린
    -0.06
    stell
    -0.06
     زن
    -0.06
     BED
    -0.06
     Sink
    -0.06
     advocated
    -0.06
     poisoning
    -0.06
    ap
    -0.06
    xis
    -0.06
    POSITIVE LOGITS
    "She
    0.06
    ),
↵
    0.06
     barcelona
    0.06
    20
    0.06
    ./
    0.06
     fresh
    0.06
    Une
    0.06
    .News
    0.06
    'ex
    0.06
     відпов
    0.06
    Act Density 0.029%

    No Known Activations