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

    Neuronpedia

    INDEX
    Explanations

    convolution

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    $fdata
    -0.08
    realloc
    -0.07
    -Muslim
    -0.07
    .getResources
    -0.07
    plorer
    -0.07
     Tara
    -0.07
     banned
    -0.07
     priesthood
    -0.07
    STEM
    -0.06
     BOTTOM
    -0.06
    POSITIVE LOGITS
     linha
    0.07
    inv
    0.07
    nox
    0.07
    ov
    0.07
    ays
    0.07
    enville
    0.07
    shade
    0.06
    卷
    0.06
     meets
    0.06
    ev
    0.06
    Act Density 0.006%

    No Known Activations