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

    Neuronpedia

    INDEX
    Explanations

    mean

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    λιο
    -0.08
    Roger
    -0.07
    サイ
    -0.07
    isel
    -0.07
     조
    -0.07
     Stre
    -0.07
    ilihan
    -0.06
    edii
    -0.06
     rally
    -0.06
    rové
    -0.06
    POSITIVE LOGITS
     means
    0.18
     meant
    0.16
     mean
    0.15
    means
    0.11
     Means
    0.11
     Mean
    0.09
    mean
    0.09
    meaning
    0.08
     Meaning
    0.08
     meaning
    0.08
    Act Density 0.029%

    No Known Activations