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

    Neuronpedia

    INDEX
    Explanations

    git commit messages for fixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     decreed
    0.46
     exerted
    0.42
     illustrious
    0.41
     imposed
    0.40
     Surg
    0.40
    ന്ഥ
    0.40
     afforded
    0.39
     Nationals
    0.39
     stipulated
    0.38
     Trench
    0.38
    POSITIVE LOGITS
    𝙿
    0.47
     webcam
    0.45
    普
    0.44
    }=$
    0.43
    同行
    0.42
    㠱
    0.42
     プ
    0.41
     ร้าน
    0.41
     النهائية
    0.41
     वेब
    0.41
    Act Density 0.000%

    No Known Activations