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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Angela
    -0.07
    Э
    -0.07
    省
    -0.06
     или
    -0.06
    bish
    -0.06
    -coordinate
    -0.06
    _AND
    -0.06
    aload
    -0.06
    фик
    -0.06
    eacher
    -0.06
    POSITIVE LOGITS
     Buccane
    0.06
     StringComparison
    0.06
    Availability
    0.06
     볼
    0.06
     которой
    0.06
     شود
    0.06
     Disconnect
    0.06
     calam
    0.06
    Protocol
    0.06
    .Cascade
    0.06
    Act Density 0.301%

    No Known Activations