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

    Neuronpedia

    INDEX
    Explanations

    Row

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Muon
    -0.07
    iffany
    -0.07
    alarında
    -0.07
     фото
    -0.06
     Kunden
    -0.06
    手を
    -0.06
    ляются
    -0.06
    ||↵
    -0.06
     sonunda
    -0.06
     هش
    -0.06
    POSITIVE LOGITS
     spa
    0.07
     recipe
    0.07
    ６
    0.06
     Emirates
    0.06
    aceous
    0.06
    acer
    0.06
    _Profile
    0.06
    grey
    0.06
     accent
    0.06
    .GetComponent
    0.06
    Act Density 0.009%

    No Known Activations