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

    Neuronpedia

    INDEX
    Explanations

    code and bacteria names

    np_acts-logits-general · gemini-2.5-flash-lite

    code identifiers related to entry points in software applications.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Negative Logits
     র
    -0.81
     wsp
    -0.79
    чая
    -0.77
     bonitas
    -0.77
    一秒
    -0.76
    开头
    -0.76
     kwietnia
    -0.75
     escalada
    -0.75
    itä
    -0.75
     傳
    -0.73
    POSITIVE LOGITS
     PRESENT
    0.82
    ⊥
    0.79
    present
    0.78
    搓
    0.75
    mA
    0.71
    斯基
    0.71
    PRESENT
    0.70
     Flin
    0.70
    قول
    0.69
     pherom
    0.68
    Act Density 0.053%

    No Known Activations