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

    Neuronpedia

    INDEX
    Explanations

    package main

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     be
    0.80
     ба
    0.79
     địa
    0.76
     pintura
    0.76
     southeastern
    0.73
     も
    0.73
     máxima
    0.72
    ;
    0.71
     automática
    0.71
     peanut
    0.71
    POSITIVE LOGITS
    im
    1.18
    us
    1.08
    ד
    1.01
    ח
    1.00
    ל
    0.97
    package
    0.93
    un
    0.93
    ع
    0.93
    ag
    0.91
    ע
    0.88
    Act Density 0.022%

    No Known Activations