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

    Neuronpedia

    INDEX
    Explanations

    code structure fragments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    気持ち
    0.44
     محبت
    0.42
    フォル
    0.40
    냔
    0.39
     venant
    0.39
    સ
    0.37
    oinette
    0.37
     acesta
    0.36
    সর
    0.36
    Sept
    0.35
    POSITIVE LOGITS
     REF
    0.45
     Collie
    0.45
     DEAL
    0.43
    itre
    0.39
     Terra
    0.38
    hyd
    0.38
     cuff
    0.38
     urea
    0.37
    yd
    0.37
     RET
    0.37
    Act Density 0.001%

    No Known Activations