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

    Neuronpedia

    INDEX
    Explanations

    Non-English text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fragment
    -0.07
     selling
    -0.06
    mkdir
    -0.06
     Woods
    -0.06
     Gladiator
    -0.06
    Locator
    -0.06
     Crime
    -0.06
    存在
    -0.06
    _',
    -0.06
     iterative
    -0.06
    POSITIVE LOGITS
    _USB
    0.08
    ;?>↵
    0.08
     unconstitutional
    0.07
     Viagra
    0.06
    ,None
    0.06
    ))^
    0.06
     iNdEx
    0.06
    unsigned
    0.06
    .geo
    0.06
    anax
    0.06
    Act Density 0.004%

    No Known Activations