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

    Neuronpedia

    INDEX
    Explanations

    Academic/formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     defenseman
    -0.07
     Holt
    -0.07
     Alonso
    -0.07
     מהמערכת
    -0.06
     onclick
    -0.06
    וגל
    -0.06
    踅
    -0.06
    upil
    -0.06
    /*******************************************************************************↵
    -0.06
    uffling
    -0.06
    POSITIVE LOGITS
     finest
    0.08
    punk
    0.08
    -flat
    0.08
     advantages
    0.07
    差点
    0.07
     wys
    0.07
     væ
    0.07
    furt
    0.07
    bab
    0.07
     aquatic
    0.07
    Act Density 0.263%

    No Known Activations