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

    Neuronpedia

    INDEX
    Explanations

    Financial and technical reports

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     TYPO
    -0.07
     aconte
    -0.07
    gó
    -0.07
    posição
    -0.07
    踞
    -0.07
    Completion
    -0.07
     McDonald
    -0.07
    Shortcut
    -0.07
     grep
    -0.07
    expl
    -0.07
    POSITIVE LOGITS
     Rx
    0.07
    :''
    0.06
     wanting
    0.06
    .getBody
    0.06
    水平
    0.06
    $v
    0.06
    )
↵
↵
↵
    0.06
     integrating
    0.06
    ↵
↵
↵
    0.06
    싴
    0.06
    Act Density 0.000%

    No Known Activations