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

    Neuronpedia

    INDEX
    Explanations

    zero

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rawl
    -0.07
    ्ड
    -0.07
     Lantern
    -0.06
     hurts
    -0.06
    Zero
    -0.06
     balls
    -0.06
    __).
    -0.06
     infant
    -0.06
     |>
    -0.06
    .pose
    -0.06
    POSITIVE LOGITS
    LLU
    0.06
    クラブ
    0.06
     drž
    0.06
     careless
    0.06
     Elemental
    0.06
    ิย
    0.06
    radan
    0.06
    "/></
    0.06
     громадян
    0.06
     the
    0.05
    Act Density 0.002%

    No Known Activations