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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     wool
    -0.07
    쌉
    -0.07
     Cap
    -0.07
     Woody
    -0.07
    _ary
    -0.06
     deber
    -0.06
    -May
    -0.06
     archivo
    -0.06
    uras
    -0.06
    ᡍ
    -0.06
    POSITIVE LOGITS
     evident
    0.08
    “
    0.07
    Frequency
    0.07
    Insn
    0.07
    Ò
    0.07
    ...");
↵
    0.07
    .svg
    0.07
     });↵↵↵↵
    0.07
    我校
    0.07
     Coming
    0.07
    Act Density 0.008%

    No Known Activations