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

    Neuronpedia

    INDEX
    Explanations

    follows

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kolo
    -0.06
     Cbd
    -0.06
    _ind
    -0.06
    .small
    -0.06
     Icon
    -0.06
    flater
    -0.06
    قى
    -0.06
     slated
    -0.06
     X
    -0.06
     resposta
    -0.06
    POSITIVE LOGITS
     téléphone
    0.07
     OVER
    0.06
    -help
    0.06
    ในการ
    0.06
    GN
    0.06
    -two
    0.06
    aza
    0.06
    /settings
    0.06
    �
    0.06
    امج
    0.06
    Act Density 0.019%

    No Known Activations