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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    회의
    -0.08
     Universidad
    -0.07
     reads
    -0.07
    covers
    -0.07
    thew
    -0.07
     differentiation
    -0.07
     세계
    -0.07
    276
    -0.06
     austerity
    -0.06
    ::::::::::::::::
    -0.06
    POSITIVE LOGITS
     boon
    0.06
    olumes
    0.06
     -*-↵↵
    0.06
     blockDim
    0.06
     Cabin
    0.06
     MOD
    0.06
    ॉड
    0.06
     ưu
    0.06
     guar
    0.06
    MethodImpl
    0.05
    Act Density 0.001%

    No Known Activations