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

    Neuronpedia

    INDEX
    Explanations

    help

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Interesting
    -0.07
    imity
    -0.07
     strike
    -0.07
    科技进步
    -0.06
    Ұ
    -0.06
    oggled
    -0.06
     DataGridViewCellStyle
    -0.06
    弇
    -0.06
     magistrate
    -0.06
    铃
    -0.06
    POSITIVE LOGITS
     Tub
    0.08
    餐馆
    0.07
    右手
    0.07
     bathtub
    0.07
    .related
    0.07
    运河
    0.07
     trời
    0.07
    ;br
    0.07
    ꡑ
    0.07
    /connect
    0.07
    Act Density 0.023%

    No Known Activations