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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     babes
    -0.07
     требования
    -0.07
     decre
    -0.07
     Cave
    -0.07
     stre
    -0.07
    EE
    -0.07
     give
    -0.07
     кня
    -0.07
    xFE
    -0.07
    iterate
    -0.07
    POSITIVE LOGITS
    on
    0.13
    On
    0.12
     On
    0.12
    ON
    0.12
     ON
    0.12
    .On
    0.12
    -On
    0.10
    _ON
    0.10
    .on
    0.09
    _On
    0.09
    Act Density 0.031%

    No Known Activations