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

    Neuronpedia

    INDEX
    Explanations

    connecting words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     podium
    -0.07
    羔
    -0.07
    Clear
    -0.07
    aupt
    -0.07
     מחיר
    -0.07
    石家庄
    -0.06
    edu
    -0.06
    眉毛
    -0.06
    .makeText
    -0.06
    重心
    -0.06
    POSITIVE LOGITS
    }):
    0.07
    ﯲ
    0.07
     RANGE
    0.07
    .↵↵↵↵↵↵↵↵↵↵
    0.07
    _axis
    0.06
     puss
    0.06
    ')">
    0.06
    olo
    0.06
    thic
    0.06
    吼
    0.06
    Act Density 0.063%

    No Known Activations