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

    Neuronpedia

    INDEX
    Explanations

    Ar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lapping
    -0.06
    xad
    -0.06
    Purchase
    -0.06
    .unlock
    -0.06
    ۱
    -0.06
     Photographer
    -0.05
     유지
    -0.05
     ⟨
    -0.05
     мас
    -0.05
    keley
    -0.05
    POSITIVE LOGITS
    ))"↵
    0.08
    _processing
    0.06
    ी,
    0.06
    解决
    0.06
    /post
    0.06
    !=↵
    0.06
    .Allow
    0.06
     shortage
    0.06
    woke
    0.06
    Ascii
    0.06
    Act Density 0.055%

    No Known Activations