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

    Neuronpedia

    INDEX
    Explanations

    Powerpoint/presentation code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     behaving
    -0.08
    _ITEM
    -0.07
    _consumer
    -0.07
    DatePicker
    -0.07
    /tags
    -0.07
     trades
    -0.07
    נחל
    -0.07
    璬
    -0.07
     الكبرى
    -0.07
    _indexes
    -0.07
    POSITIVE LOGITS
     base
    0.07
     RAID
    0.07
    產生
    0.07
    ret
    0.07
     perception
    0.07
    ڎ
    0.07
    벅
    0.07
    为你
    0.06
    □
    0.06
    reten
    0.06
    Act Density 0.002%

    No Known Activations