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

    Neuronpedia

    INDEX
    Explanations

    Code related to data processing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Models
    -0.07
    DEBUG
    -0.07
    -news
    -0.07
     objects
    -0.07
    128
    -0.07
    征
    -0.07
    िं
    -0.07
    _velocity
    -0.07
    observations
    -0.06
    _dep
    -0.06
    POSITIVE LOGITS
     crud
    0.06
     sc
    0.06
    Rpc
    0.06
    御
    0.06
     confirming
    0.05
    окумент
    0.05
     kor
    0.05
     ł
    0.05
     nejd
    0.05
     ním
    0.05
    Act Density 0.030%

    No Known Activations