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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     LOSS
    -0.08
    reds
    -0.07
    urch
    -0.07
    Venue
    -0.06
    Implementation
    -0.06
     spokesperson
    -0.06
     CH
    -0.06
    team
    -0.06
    $output
    -0.06
    mental
    -0.06
    POSITIVE LOGITS
     iov
    0.06
     пи
    0.06
    _undo
    0.06
     sailors
    0.06
     yeter
    0.06
    اف
    0.06
     angl
    0.06
     Banco
    0.06
     consort
    0.06
     cherry
    0.06
    Act Density 0.049%

    No Known Activations