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

    Neuronpedia

    INDEX
    Explanations

    type

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    én
    -0.07
    ry
    -0.06
    icides
    -0.06
    システム
    -0.06
     事
    -0.06
    нем
    -0.06
     interpersonal
    -0.06
    _fh
    -0.06
     ink
    -0.06
     متر
    -0.06
    POSITIVE LOGITS
    /Graphics
    0.07
    Poss
    0.06
    сько
    0.06
    ِي
    0.06
     thousand
    0.06
     pigeon
    0.06
    iPhone
    0.06
     desta
    0.06
                 ↵
    0.06
    izzato
    0.06
    Act Density 0.003%

    No Known Activations