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
    .FloatField
    -0.07
    “我
    -0.06
     &,
    -0.06
     Ambient
    -0.06
    ющего
    -0.06
    /*----------------------------------------------------------------------------
    -0.06
    사지
    -0.06
     Tür
    -0.06
    Firebase
    -0.06
     Belarus
    -0.06
    POSITIVE LOGITS
     SNP
    0.07
     đủ
    0.06
    OPTIONS
    0.06
     mayores
    0.06
    BOOLE
    0.06
     denied
    0.06
     beyond
    0.06
     дня
    0.06
     aşam
    0.06
    ีด
    0.06
    Act Density 0.032%

    No Known Activations