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

    Neuronpedia

    INDEX
    Explanations

    place names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     condi
    -0.06
    "){↵
    -0.06
    аем
    -0.06
    '){↵
    -0.06
     měsí
    -0.06
     endl
    -0.06
    Credit
    -0.06
    modules
    -0.06
    Aceptar
    -0.06
     gulp
    -0.06
    POSITIVE LOGITS
     pav
    0.06
     Manor
    0.06
    دة
    0.06
    oller
    0.06
     cafe
    0.06
    اظ
    0.06
     výro
    0.06
    /ge
    0.06
     coeff
    0.06
     femmes
    0.06
    Act Density 0.052%

    No Known Activations