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

    Neuronpedia

    INDEX
    Explanations

    island, stranded

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Feel
    -0.07
     розповід
    -0.06
    ApiOperation
    -0.06
    га
    -0.06
    _me
    -0.06
     showAlert
    -0.06
     coch
    -0.06
     interf
    -0.06
    ,model
    -0.06
     مقد
    -0.06
    POSITIVE LOGITS
     stranded
    0.08
    OMUX
    0.08
    .gstatic
    0.07
    θηκε
    0.06
    .baidu
    0.06
     سخت
    0.06
    νος
    0.06
    auc
    0.06
    Tôi
    0.06
    adapter
    0.06
    Act Density 0.008%

    No Known Activations