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

    Neuronpedia

    INDEX
    Explanations

    updates post-release

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     stimuli
    0.42
     theat
    0.40
    टेट
    0.39
    欝
    0.38
    habilit
    0.38
     devise
    0.37
    cim
    0.37
     discomfort
    0.37
    OnOff
    0.36
     هایی
    0.36
    POSITIVE LOGITS
     strapping
    0.45
     strapped
    0.43
    ฝ่าย
    0.43
    তিরিক্ত
    0.41
     WHILE
    0.41
    フリー
    0.40
     கூடுதலாக
    0.39
     கிடைத்த
    0.39
     HAVING
    0.38
    twenty
    0.38
    Act Density 0.001%

    No Known Activations