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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     serious
    -0.06
    (va
    -0.06
     unintended
    -0.06
    Suffix
    -0.06
     receiving
    -0.06
    [a
    -0.06
    (mac
    -0.06
    FA
    -0.06
    -Dec
    -0.06
    _wallet
    -0.06
    POSITIVE LOGITS
    ís
    0.07
     욕
    0.07
    然而
    0.07
     ช
    0.06
     लड़क
    0.06
    ediği
    0.06
    Công
    0.06
     ExecutionContext
    0.06
     Tor
    0.06
    .SpringBootApplication
    0.06
    Act Density 0.008%

    No Known Activations