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

    Neuronpedia

    INDEX
    Explanations

    say capital letters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ))?
    -0.07
    球队
    -0.07
    (horizontal
    -0.07
    utch
    -0.07
    比较多
    -0.07
    ꪼ
    -0.07
    /native
    -0.07
    nger
    -0.07
    debit
    -0.07
     etter
    -0.07
    POSITIVE LOGITS
    _stdout
    0.07
    곳
    0.07
    _public
    0.07
    祓
    0.07
    อำเภ
    0.07
     strchr
    0.07
     resilience
    0.07
     ścian
    0.07
    ERC
    0.07
    .Struct
    0.07
    Act Density 0.012%

    No Known Activations