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

    Neuronpedia

    INDEX
    Explanations

    code block delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    izable
    0.27
    ете
    0.27
    장의
    0.27
    γκε
    0.27
    δας
    0.26
    िर
    0.26
    ደም
    0.25
     ؛
    0.25
    Maker
    0.25
    contentText
    0.25
    POSITIVE LOGITS
     See
    0.42
     However
    0.37
     Examples
    0.35
     Jangan
    0.34
     Dont
    0.34
    see
    0.34
     Put
    0.34
     Lihat
    0.34
    examples
    0.34
     DON
    0.34
    Act Density 0.000%

    No Known Activations