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

    Neuronpedia

    INDEX
    Explanations

    end of excel column

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     лі
    0.41
     ¹
    0.41
    keywords
    0.41
    cached
    0.39
    ActivityResult
    0.38
    inputStream
    0.37
    ename
    0.37
     keywords
    0.36
    HANDLER
    0.36
    žena
    0.36
    POSITIVE LOGITS
     farther
    0.43
     consecut
    0.43
     Dw
    0.39
     Saddle
    0.39
     apariencia
    0.38
     Grain
    0.38
     verl
    0.37
     પોલી
    0.37
     домой
    0.37
     aparência
    0.37
    Act Density 0.002%

    No Known Activations