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

    Neuronpedia

    INDEX
    Explanations

    svg code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     you
    0.62
     леса
    0.57
    ER
    0.57
     children
    0.54
     It
    0.53
    ੇ
    0.53
     Social
    0.52
     pathogens
    0.52
    giveness
    0.52
     context
    0.52
    POSITIVE LOGITS
    uno
    0.60
    scm
    0.59
    issime
    0.58
    쥬
    0.55
    uiu
    0.55
    હ
    0.54
    🤩
    0.54
    uil
    0.54
    <unused2173>
    0.54
    hk
    0.53
    Act Density 0.000%

    No Known Activations