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

    Neuronpedia

    INDEX
    Explanations

    ="

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Surely
    -0.07
    524
    -0.06
    937
    -0.06
    ITES
    -0.06
     frantic
    -0.06
    769
    -0.06
    579
    -0.06
    -sub
    -0.06
    ělí
    -0.06
    hões
    -0.06
    POSITIVE LOGITS
    ạt
    0.07
    patible
    0.07
     actresses
    0.06
     duke
    0.06
    "class
    0.06
    'field
    0.06
     "\↵
    0.06
     พล
    0.06
    .cwd
    0.06
    $I
    0.06
    Act Density 0.004%

    No Known Activations