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

    Neuronpedia

    INDEX
    Explanations

    clients

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     soar
    -0.08
    寇
    -0.07
     science
    -0.07
    —with
    -0.07
    保
    -0.07
     of
    -0.07
     Forest
    -0.06
     Opens
    -0.06
    使用寿命
    -0.06
     captured
    -0.06
    POSITIVE LOGITS
    �
    0.07
     prestige
    0.07
     clients
    0.07
     CHO
    0.07
     ник
    0.07
     flirting
    0.07
     platinum
    0.07
     demasi
    0.07
     protagonist
    0.07
    ⟩
    0.07
    Act Density 0.031%

    No Known Activations