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

    Neuronpedia

    INDEX
    Explanations

    Story/movie descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inher
    -0.07
    /env
    -0.07
    okud
    -0.07
    -sp
    -0.07
     delegated
    -0.06
    \">↵
    -0.06
    stp
    -0.06
     Placeholder
    -0.06
     profiles
    -0.06
    ьогод
    -0.06
    POSITIVE LOGITS
    だな
    0.06
    GeV
    0.06
    _IT
    0.06
     frau
    0.06
     giden
    0.06
     избав
    0.06
     July
    0.06
     обрат
    0.06
     {{$
    0.06
    ünkü
    0.06
    Act Density 0.020%

    No Known Activations