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

    Neuronpedia

    INDEX
    Explanations

    key, gravity, fast, draw, put, latest, set

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ం
    0.91
    museum
    0.78
    ം
    0.77
    ை
    0.75
     Calibri
    0.73
     стекла
    0.73
    mö
    0.73
    Selecion
    0.71
    lç
    0.71
    m
    0.71
    POSITIVE LOGITS
     prolific
    0.80
    9
    0.78
    爲
    0.76
     presion
    0.75
     apropi
    0.75
    ന്റെ
    0.74
     reign
    0.74
    朋
    0.74
     portant
    0.73
    utory
    0.72
    Act Density 0.001%

    No Known Activations