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

    Neuronpedia

    INDEX
    Explanations

    modifier keys

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -faced
    -0.08
    fir
    -0.07
     sparse
    -0.07
    .ix
    -0.07
     سنة
    -0.07
    部落
    -0.07
    -0.07
     ма
    -0.07
    finger
    -0.07
    ลำ
    -0.07
    POSITIVE LOGITS
    _selector
    0.07
    Você
    0.07
     serait
    0.07
    issors
    0.07
    对方
    0.07
    .communic
    0.06
    莴
    0.06
    低于
    0.06
    estic
    0.06
    Hover
    0.06
    Act Density 0.005%

    No Known Activations