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

    Neuronpedia

    INDEX
    Explanations

    Technical/Legal/Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ственной
    -0.06
    ovie
    -0.06
     alphabet
    -0.06
    .branch
    -0.06
     Uncle
    -0.06
     proceedings
    -0.06
    -0.06
     bothers
    -0.06
    firstname
    -0.06
    Foo
    -0.06
    POSITIVE LOGITS
    /{}/
    0.07
     ключ
    0.07
    Cert
    0.07
    _trap
    0.06
    DEPEND
    0.06
    ocumented
    0.06
    将
    0.06
    ripp
    0.06
    (-(
    0.06
    $num
    0.06
    Act Density 0.001%

    No Known Activations