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

    Neuronpedia

    INDEX
    Explanations

    Titan

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Wei
    -0.07
    (Keys
    -0.07
    سب
    -0.06
    幅
    -0.06
    PIO
    -0.06
    赤
    -0.06
    가지
    -0.06
    개의
    -0.06
    样子
    -0.06
    .LENGTH
    -0.06
    POSITIVE LOGITS
     pož
    0.07
     filler
    0.07
     fifty
    0.07
     disillusion
    0.06
    .CreateTable
    0.06
     retiring
    0.06
     Dort
    0.06
     dictate
    0.06
     collar
    0.06
    Telegram
    0.06
    Act Density 0.001%

    No Known Activations