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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    piler
    -0.08
    алог
    -0.07
    Junior
    -0.07
     digitalWrite
    -0.06
    (steps
    -0.06
     мор
    -0.06
     therap
    -0.06
    氏
    -0.06
     Стар
    -0.06
     runes
    -0.06
    POSITIVE LOGITS
    (SYS
    0.07
    까
    0.06
     VG
    0.06
     많은
    0.06
    (selected
    0.06
    .lv
    0.06
     OF
    0.06
     delic
    0.06
     enumerate
    0.06
     hydrogen
    0.06
    Act Density 0.403%

    No Known Activations