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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ⯑
    -0.08
    >'.↵
    -0.07
    顧
    -0.07
    𫸩
    -0.07
    ='${
    -0.07
    🌁
    -0.06
    ṝ
    -0.06
    ⟰
    -0.06
    睇
    -0.06
     lut
    -0.06
    POSITIVE LOGITS
    semb
    0.08
    stinence
    0.08
     amber
    0.08
     casino
    0.08
    Mirror
    0.07
     elabor
    0.07
     Hel
    0.07
     VARIANT
    0.07
    (prediction
    0.07
    ernals
    0.07
    Act Density 0.015%

    No Known Activations