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

    Neuronpedia

    INDEX
    Explanations

    Epstein

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ﳏ
    -0.08
    מע
    -0.07
    atetime
    -0.07
    臑
    -0.07
    guild
    -0.07
     triggering
    -0.07
    腚
    -0.06
    𫘦
    -0.06
    ooke
    -0.06
    扭
    -0.06
    POSITIVE LOGITS
    Little
    0.07
    With
    0.07
    博览
    0.07
     entert
    0.07
    ●
    0.07
    état
    0.06
     enlarge
    0.06
    ...,
    0.06
     Plate
    0.06
    Having
    0.06
    Act Density 0.002%

    No Known Activations