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

    Neuronpedia

    INDEX
    Explanations

    taking an action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     กำ
    0.42
     ներ
    0.40
    Experience
    0.39
    Use
    0.37
     تنا
    0.36
    Usage
    0.35
    CAPTURE
    0.35
     Usage
    0.35
    脱
    0.35
     ذكر
    0.35
    POSITIVE LOGITS
     backseat
    0.74
     plunge
    0.71
     liberties
    0.69
     leap
    0.68
     advantage
    0.68
     precautions
    0.67
     cue
    0.64
     initiative
    0.63
     stab
    0.60
     stance
    0.59
    Act Density 0.014%

    No Known Activations