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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (kwargs
    -0.07
     pozdě
    -0.06
     strokeLine
    -0.06
     yans
    -0.06
     fodder
    -0.06
     �
    -0.06
    (chain
    -0.06
    .star
    -0.06
     sed
    -0.06
     supremacy
    -0.06
    POSITIVE LOGITS
     enlarge
    0.08
     enlarg
    0.07
     tamaño
    0.07
     tamanho
    0.07
    urret
    0.07
     taille
    0.07
    scaled
    0.07
     monstrous
    0.07
    ItemAt
    0.07
     Scarlet
    0.07
    Act Density 0.049%

    No Known Activations