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

    Neuronpedia

    INDEX
    Explanations

    He plus common words/names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tip
    0.83
    s
    0.81
     المتحدة
    0.81
     тенден
    0.81
    REQUIRE
    0.79
     Poco
    0.79
    쥐
    0.78
     unu
    0.78
     zm
    0.77
     tougher
    0.77
    POSITIVE LOGITS
    uristic
    1.58
    athy
    1.37
    aping
    1.36
    倆
    1.34
    ureux
    1.29
    idi
    1.27
    irlo
    1.25
    dule
    1.24
    ilig
    1.23
    brew
    1.23
    Act Density 0.061%

    No Known Activations