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

    Neuronpedia

    INDEX
    Explanations

    INCLUDING

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     redes
    -0.08
    :The
    -0.07
     del
    -0.06
    :model
    -0.06
    .Code
    -0.06
    flash
    -0.06
     �
    -0.06
    .${
    -0.06
     Has
    -0.06
    大家都在
    -0.06
    POSITIVE LOGITS
    Vectorizer
    0.08
    椒
    0.07
    icionar
    0.07
    옮
    0.07
    orraine
    0.07
    gorit
    0.07
     inmate
    0.07
     Jazeera
    0.07
     onAnimation
    0.07
    会影响
    0.07
    Act Density 0.001%

    No Known Activations