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

    Neuronpedia

    INDEX
    Explanations

    shy, hesitant, fearful

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     it
    0.57
     It
    0.53
    sel
    0.53
    arde
    0.52
     Пет
    0.51
    theta
    0.49
    tion
    0.49
    vart
    0.49
    tered
    0.49
    ेल
    0.48
    POSITIVE LOGITS
    ر
    0.79
     hesitate
    0.71
    اك
    0.70
    مي
    0.67
     reluctance
    0.66
    EN
    0.61
     hesitant
    0.61
     reluctantly
    0.61
    ARE
    0.61
    ↵
    0.60
    Act Density 0.381%

    No Known Activations