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
    деся
    -0.07
    su
    -0.07
    שיו
    -0.07
    lassian
    -0.07
     Lions
    -0.07
     עושה
    -0.07
    指责
    -0.07
    村村民
    -0.06
    指
    -0.06
    ｈ
    -0.06
    POSITIVE LOGITS
     фл
    0.08
     controlling
    0.07
    闲
    0.07
     VIP
    0.07
     webcam
    0.07
    тел
    0.07
    .tables
    0.07
    ån
    0.07
    itat
    0.07
     tables
    0.07
    Act Density 0.012%

    No Known Activations