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

    Neuronpedia

    INDEX
    Explanations

    prepositions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     helfen
    -0.07
    ificado
    -0.06
    ,A
    -0.06
     detta
    -0.06
    isNaN
    -0.06
    .Enc
    -0.06
     purposes
    -0.06
    three
    -0.06
     Dabei
    -0.06
     Solomon
    -0.06
    POSITIVE LOGITS
     المد
    0.07
     Represents
    0.07
    uyết
    0.06
    _FLAGS
    0.06
    OWER
    0.06
    умент
    0.06
    ους
    0.06
     Fight
    0.06
    режд
    0.06
    opers
    0.06
    Act Density 0.027%

    No Known Activations