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

    Neuronpedia

    INDEX
    Explanations

    numbers and calculations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    耒
    0.38
     Edel
    0.36
     अडानी
    0.35
     Puff
    0.35
     realizing
    0.34
    KeepOriginal
    0.34
    IANA
    0.34
     realising
    0.34
     Integra
    0.34
    ]$;
    0.34
    POSITIVE LOGITS
     monstros
    0.48
    HCC
    0.47
     monstrous
    0.46
    pril
    0.40
    RCC
    0.39
    寻
    0.39
    MCC
    0.38
    尋
    0.38
     Collin
    0.38
    整理
    0.38
    Act Density 0.002%

    No Known Activations