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

    Neuronpedia

    INDEX
    Explanations

    generic internet text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     owe
    -0.07
     女
    -0.07
     škol
    -0.07
     ettiği
    -0.06
     sinh
    -0.06
    ارا
    -0.06
     خویش
    -0.06
     sempre
    -0.06
     육
    -0.06
     Gh
    -0.06
    POSITIVE LOGITS
     Anything
    0.07
     dinosaur
    0.06
    λια
    0.06
    (Parameter
    0.06
     постав
    0.06
    .setRequestHeader
    0.06
     tipo
    0.06
    ifornia
    0.06
    ruise
    0.06
    Framebuffer
    0.06
    Act Density 0.000%

    No Known Activations