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

    Neuronpedia

    INDEX
    Explanations

    huggingface.co links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     highly
    0.71
     horribly
    0.69
     molybdenum
    0.68
     popping
    0.68
     hundred
    0.67
     auto
    0.67
     최
    0.66
     चले
    0.66
     hello
    0.65
     immensely
    0.65
    POSITIVE LOGITS
    сно
    0.74
    拵
    0.74
    વાનો
    0.73
    лардан
    0.73
    𒄩
    0.67
    طف
    0.67
    emun
    0.66
    consent
    0.65
    ὔ
    0.65
    进步
    0.65
    Act Density 0.063%

    No Known Activations