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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .multiply
    -0.07
    _DAT
    -0.07
    .EVT
    -0.07
    慎
    -0.06
    .coroutines
    -0.06
    無しさん
    -0.06
    amus
    -0.06
     кап
    -0.06
     domains
    -0.06
     엄
    -0.06
    POSITIVE LOGITS
    (^
    0.07
     letting
    0.07
    €™
    0.07
     unsupported
    0.06
    ivers
    0.06
     now
    0.06
     pistol
    0.06
     D
    0.06
     try
    0.06
    |[
    0.06
    Act Density 0.000%

    No Known Activations