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

    Neuronpedia

    INDEX
    Explanations

    abstract concepts

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    သွယ်
    0.63
    <0xBB>
    0.57
    casualties
    0.57
     покупки
    0.55
    诲
    0.55
    ור
    0.54
    domestic
    0.53
    𝑇
    0.53
     traumas
    0.51
     гале
    0.50
    POSITIVE LOGITS
     aya
    0.68
    哇
    0.67
    okinase
    0.66
     jira
    0.61
    icoter
    0.59
     dependiendo
    0.59
     pretext
    0.59
    рма
    0.59
    spunkt
    0.59
     postura
    0.58
    Act Density 0.000%

    No Known Activations