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

    Neuronpedia

    INDEX
    Explanations

    turn off/on

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Longer
    0.75
    Distributed
    0.73
    longer
    0.72
    ભા
    0.72
    安排
    0.70
     제거
    0.69
    ffiche
    0.68
    -_-
    0.68
     mitigated
    0.67
    पटना
    0.67
    POSITIVE LOGITS
     thiện
    0.68
     kerajaan
    0.68
    র্যের
    0.65
    ার
    0.65
    රු
    0.64
    もので
    0.64
     pagina
    0.63
    𝑵
    0.63
    மணிய
    0.62
    nym
    0.62
    Act Density 0.070%

    No Known Activations