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

    Neuronpedia

    INDEX
    Explanations

    Foreign language characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    epsilon
    -0.07
     Na
    -0.07
     Guru
    -0.07
     vertical
    -0.06
     forward
    -0.06
    ORMAT
    -0.06
     bra
    -0.06
     пош
    -0.06
     Поч
    -0.06
    Detect
    -0.06
    POSITIVE LOGITS
     कन
    0.07
    _Link
    0.07
    postalcode
    0.07
    uide
    0.07
     '/'↵
    0.07
    essed
    0.06
    दर
    0.06
    fgang
    0.06
    lady
    0.06
    isay
    0.06
    Act Density 0.027%

    No Known Activations