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

    Neuronpedia

    INDEX
    Explanations

    providers and partners

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    OV
    -0.07
    Won
    -0.07
    accion
    -0.06
     cambiar
    -0.06
     saf
    -0.06
    .Commit
    -0.06
    Ax
    -0.06
     lept
    -0.06
    ald
    -0.06
     anarchist
    -0.06
    POSITIVE LOGITS
    ？
    0.07
    963
    0.07
    $instance
    0.06
    ै?
    0.06
    �
    0.06
    DirectoryName
    0.06
     места
    0.06
    Translatef
    0.06
    ुं
    0.06
     لباس
    0.06
    Act Density 0.006%

    No Known Activations