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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Angus
    -0.06
     typical
    -0.06
     finanční
    -0.06
    ElapsedTime
    -0.06
     fins
    -0.06
     ekonomik
    -0.06
     viewWillAppear
    -0.06
     outlining
    -0.06
    mid
    -0.06
     cwd
    -0.05
    POSITIVE LOGITS
     Advent
    0.07
     dismantle
    0.07
     inne
    0.07
     Social
    0.07
    자는
    0.07
     şiddet
    0.07
     snag
    0.06
     Created
    0.06
     deserialize
    0.06
    句
    0.06
    Act Density 0.036%

    No Known Activations