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

    Neuronpedia

    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ccp
    -0.07
     Gra
    -0.07
    ф
    -0.06
    IIIK
    -0.06
    corr
    -0.06
     전용면적
    -0.06
     MU
    -0.06
    F
    -0.06
    loha
    -0.06
     BF
    -0.06
    POSITIVE LOGITS
    -efficient
    0.07
    getDoctrine
    0.06
    ileged
    0.06
     nová
    0.06
     свое
    0.06
    やる夫
    0.06
    ITableView
    0.06
    antage
    0.06
     Illuminate
    0.06
    .folder
    0.06
    Act Density 0.014%

    No Known Activations