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

    Neuronpedia

    INDEX
    Explanations

    time/sequence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ียรต
    -0.07
     Liberal
    -0.07
     Contributor
    -0.07
    ificates
    -0.06
    .raise
    -0.06
    VISION
    -0.06
     encoded
    -0.06
    _STRUCTURE
    -0.06
     Ra
    -0.06
     ($("#
    -0.06
    POSITIVE LOGITS
    同步
    0.07
    ис
    0.07
    minimum
    0.07
     applic
    0.07
    成功
    0.07
     Jonas
    0.06
    のが
    0.06
    _series
    0.06
     Gravity
    0.06
     бар
    0.06
    Act Density 0.060%

    No Known Activations