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

    Neuronpedia

    INDEX
    Explanations

    breakdown, tokenize

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vzh
    0.46
    替
    0.45
     guinea
    0.45
     ロゴ
    0.45
     第
    0.44
     carav
    0.44
    otonic
    0.42
     observable
    0.41
     однозна
    0.41
    amin
    0.41
    POSITIVE LOGITS
     Lightweight
    0.46
    Not
    0.45
    Blocked
    0.44
    मलव
    0.42
    ইন
    0.42
     Sunlight
    0.41
    <0xE3>
    0.41
     Trained
    0.41
     Blot
    0.41
    Thickness
    0.41
    Act Density 0.006%

    No Known Activations