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

    Neuronpedia

    INDEX
    Explanations

    credit limit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     جاتا
    1.70
     adjournment
    1.65
    孖
    1.65
     내용은
    1.64
    様子
    1.63
    などで
    1.62
    際は
    1.60
     columnist
    1.59
    年は
    1.59
     schemes
    1.58
    POSITIVE LOGITS
    rinsic
    2.33
     been
    2.18
     awakened
    2.16
     newfound
    2.12
    7
    2.09
     woken
    2.01
     BEEN
    2.00
     принадлежа
    1.91
    8
    1.90
     подня
    1.90
    Act Density 0.391%

    No Known Activations