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

    Neuronpedia

    INDEX
    Explanations

    body adjustments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iquer
    -0.07
    dater
    -0.07
    (cursor
    -0.07
    .proto
    -0.07
    олее
    -0.07
    бра
    -0.06
    .verbose
    -0.06
    튼
    -0.06
     bus
    -0.06
     varieties
    -0.06
    POSITIVE LOGITS
    LIK
    0.06
    ab
    0.06
     Cobb
    0.06
    heel
    0.06
    =re
    0.06
     seab
    0.06
    942
    0.05
     nj
    0.05
    ota
    0.05
    omer
    0.05
    Act Density 0.006%

    No Known Activations