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

    Neuronpedia

    INDEX
    Explanations

    say node

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    anity
    -0.07
    irement
    -0.06
     dr
    -0.06
     Den
    -0.06
    .FLAG
    -0.06
     Scan
    -0.06
    organ
    -0.06
     quick
    -0.06
     either
    -0.06
     ARC
    -0.06
    POSITIVE LOGITS
    ($('#
    0.07
    .↵↵↵↵↵
    0.06
    .getSelectionModel
    0.06
     mili
    0.06
     malfunction
    0.06
    .codehaus
    0.06
     Bers
    0.06
    备份
    0.06
     orchest
    0.06
    .palette
    0.06
    Act Density 0.014%

    No Known Activations