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

    Neuronpedia

    INDEX
    Explanations

    dysphoria or metastasis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     inteligentes
    0.91
    abele
    0.86
    <<(
    0.84
    ([^
    0.82
    дравствуйте
    0.81
     seguros
    0.80
    ො
    0.80
     ActionBar
    0.80
    forgettable
    0.80
    㴼
    0.80
    POSITIVE LOGITS
    This
    0.89
    I
    0.88
    أ
    0.79
    You
    0.75
    She
    0.73
    There
    0.69
    It
    0.68
    Il
    0.68
    يح
    0.68
     bodies
    0.66
    Act Density 0.011%

    No Known Activations