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

    Neuronpedia

    INDEX
    Explanations

    the shape of something as well as XML markup and shape-shifting

    oai_token-act-pair · gemini-2.0-flash

    shapes and matching

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     (;;
    -0.57
    hless
    -0.57
    RAINE
    -0.54
    modelBuilder
    -0.51
    sikal
    -0.50
    sitive
    -0.50
     alkal
    -0.49
    cinated
    -0.49
    iné
    -0.49
    olarmente
    -0.49
    POSITIVE LOGITS
    <bos>
    0.82
     intptr
    0.67
    thâu
    0.63
    Rujuakan
    0.61
     betweenstory
    0.57
     ModelRenderer
    0.54
    таратура
    0.53
    bentuk
    0.52
    MessageOf
    0.52
     препратки
    0.51
    Act Density 1.554%

    No Known Activations