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

    Neuronpedia

    INDEX
    Explanations

    Neural network parameters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    readonly
    -0.07
    ietf
    -0.07
    ektor
    -0.07
    _HAL
    -0.07
    FDA
    -0.06
     Auschwitz
    -0.06
     &)
    -0.06
    peek
    -0.06
     Debugger
    -0.06
     damit
    -0.06
    POSITIVE LOGITS
     아무
    0.06
     disillusion
    0.06
    ="{!!
    0.06
    ">{{$
    0.06
    /mit
    0.06
     Muss
    0.06
     नव
    0.06
     ماي
    0.06
     Mapper
    0.06
    .Imp
    0.06
    Act Density 0.027%

    No Known Activations