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

    Neuronpedia

    INDEX
    Explanations

    revealing identity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Platt
    -0.06
    163
    -0.06
         
    -0.06
     drugs
    -0.06
     مثلا
    -0.06
     الأخرى
    -0.06
    svm
    -0.06
     mortgage
    -0.06
    ені
    -0.06
    Border
    -0.06
    POSITIVE LOGITS
    .Join
    0.08
    _grade
    0.07
    .Assign
    0.07
    ="">↵
    0.06
    šil
    0.06
    /met
    0.06
    =target
    0.06
    洲
    0.06
    wechat
    0.06
    ={(
    0.06
    Act Density 0.052%

    No Known Activations