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

    Neuronpedia

    INDEX
    Explanations

    Code and conversational snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    átní
    -0.07
    xFA
    -0.06
    _Item
    -0.06
    иту
    -0.06
    ptrdiff
    -0.06
    има
    -0.06
     Christianity
    -0.06
    zh
    -0.06
     नक
    -0.06
     уз
    -0.06
    POSITIVE LOGITS
    string
    0.08
     امن
    0.07
    ARN
    0.07
     Installing
    0.07
     Ep
    0.07
    .New
    0.06
     conditioned
    0.06
    Ab
    0.06
     Palace
    0.06
     péri
    0.06
    Act Density 0.000%

    No Known Activations