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

    Neuronpedia

    INDEX
    Explanations

    immediate outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ক্রমশ
    0.48
    ROLE
    0.45
    㖅
    0.44
    あくまで
    0.43
    常に
    0.43
    正式
    0.42
    ingh
    0.42
     Buck
    0.42
     finalement
    0.42
    你自己
    0.41
    POSITIVE LOGITS
     immediate
    1.02
    immediate
    0.99
    Immediate
    0.95
    바로
    0.95
     Immediate
    0.95
     immediately
    0.93
     immedi
    0.93
    immediately
    0.92
     gratification
    0.91
     inmediata
    0.91
    Act Density 0.011%

    No Known Activations