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

    Neuronpedia

    INDEX
    Explanations

    large

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    огда
    -0.07
     що
    -0.06
     thoughtful
    -0.06
     Particip
    -0.06
     domin
    -0.06
    ًا
    -0.06
     plans
    -0.06
    `.↵
    -0.06
     Professionals
    -0.06
    _templates
    -0.06
    POSITIVE LOGITS
     salts
    0.07
    JPEG
    0.07
     Krak
    0.07
    userData
    0.07
    /{{$
    0.07
    857
    0.07
    Lİ
    0.06
    CORD
    0.06
     arab
    0.06
     εξ
    0.06
    Act Density 0.002%

    No Known Activations