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

    Neuronpedia

    INDEX
    Explanations

    no-code, no-till, no-parking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    忍不住
    0.42
    IRT
    0.40
     numerator
    0.37
     무엇
    0.36
     YOUR
    0.36
     niez
    0.36
    FD
    0.36
    不断的
    0.36
     meaningful
    0.35
    っています
    0.35
    POSITIVE LOGITS
     nor
    0.86
     sondern
    0.84
    nor
    0.84
    ဘူး
    0.78
     anymore
    0.72
    🚫
    0.72
    🙅
    0.71
     whatsoever
    0.71
     tampoco
    0.69
    ទេ។
    0.67
    Act Density 0.032%

    No Known Activations