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

    Neuronpedia

    INDEX
    Explanations

    an

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    indrome
    -0.07
     Fruit
    -0.07
     abuse
    -0.06
    centers
    -0.06
     intellectual
    -0.06
    记
    -0.06
    .stringify
    -0.06
    「お
    -0.06
    Palindrome
    -0.06
    -In
    -0.06
    POSITIVE LOGITS
     Dio
    0.06
    rió
    0.06
     pursuing
    0.06
    球
    0.06
     Р
    0.06
    ‎
    0.06
     �
    0.06
    338
    0.06
     nhiều
    0.06
    ा।
    0.06
    Act Density 0.010%

    No Known Activations