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

    Neuronpedia

    INDEX
    Explanations

    alty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .dataset
    -0.07
    hours
    -0.07
    QUOTE
    -0.07
    Hours
    -0.06
    zioni
    -0.06
    _score
    -0.06
    -source
    -0.06
     Operating
    -0.06
    Index
    -0.06
    Scripts
    -0.06
    POSITIVE LOGITS
     rebell
    0.07
    ủy
    0.06
    MUX
    0.06
     如
    0.06
    .tip
    0.06
     }↵↵
    0.06
     中国
    0.06
     Lun
    0.06
    ueblo
    0.06
     embr
    0.06
    Act Density 0.012%

    No Known Activations