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

    Neuronpedia

    INDEX
    Explanations

    file or set

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tà
    -0.08
     quindi
    -0.07
    括
    -0.07
     totalmente
    -0.07
     תלוי
    -0.07
     cualquier
    -0.07
     stos
    -0.07
     به
    -0.07
    当然是
    -0.06
    汇率
    -0.06
    POSITIVE LOGITS
     float
    0.07
    　
    0.06
    Celebr
    0.06
    yk
    0.06
    _winner
    0.06
    assium
    0.06
    瀔
    0.06
    .wav
    0.06
    ">↵↵
    0.06
    oken
    0.06
    Act Density 0.000%

    No Known Activations