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

    Neuronpedia

    INDEX
    Explanations

    cannot and will not fulfill

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     czasu
    0.57
     dreams
    0.56
    dreams
    0.55
     cilt
    0.55
     Vision
    0.55
    𝗠
    0.55
     C
    0.54
    ваме
    0.54
     w
    0.54
     PEOPLE
    0.54
    POSITIVE LOGITS
    ůli
    0.56
    aggressive
    0.55
     refused
    0.54
    (",");
    0.54
    Exam
    0.53
    ListOf
    0.53
    PhotoMode
    0.52
    ود
    0.51
    avoid
    0.49
    Entropy
    0.48
    Act Density 0.159%

    No Known Activations