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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     createState
    -0.64
    phylo
    -0.63
     GNA
    -0.61
    gisayar
    -0.58
     self
    -0.58
    Pozdrawiam
    -0.58
     geslacht
    -0.57
    urier
    -0.56
    nước
    -0.56
    pulos
    -0.56
    POSITIVE LOGITS
     sometimes
    0.46
     again
    0.44
    bootstrapcdn
    0.42
    もと
    0.42
     bits
    0.42
     până
    0.42
     parts
    0.41
    parts
    0.40
     parfois
    0.40
     bulunabilir
    0.39
    Act Density 0.005%

    No Known Activations