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

    Neuronpedia

    INDEX
    Explanations

    not contraction

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vape
    -0.07
     FUNCTION
    -0.07
    rees
    -0.06
    llu
    -0.06
    fac
    -0.06
     milk
    -0.06
    usuarios
    -0.06
    forEach
    -0.06
     relacion
    -0.06
     Egg
    -0.06
    POSITIVE LOGITS
     küçük
    0.07
    чают
    0.06
    iedade
    0.06
    エル
    0.06
     Müslüman
    0.06
     taco
    0.06
     karşı
    0.06
     hacia
    0.06
    食べ
    0.06
    ी
    0.06
    Act Density 0.012%

    No Known Activations