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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    p
    1.09
    :
    0.91
     ­
    0.84
    agl
    0.83
    c
    0.81
    aac
    0.80
    pb
    0.79
    𝙥
    0.77
    ゛
    0.77
    ﾞ
    0.76
    POSITIVE LOGITS
    LORD
    1.05
     LORD
    0.89
    lord
    0.87
     hedgehog
    0.85
     relazioni
    0.84
     TAE
    0.84
     ladle
    0.83
    сера
    0.83
     GUID
    0.83
    IDENTAL
    0.82
    Act Density 0.002%

    No Known Activations