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
    .randint
    -0.07
    透
    -0.07
     스트
    -0.07
    `t
    -0.06
    "My
    -0.06
     उम
    -0.06
     burger
    -0.06
    Chi
    -0.06
     वक
    -0.06
    quo
    -0.06
    POSITIVE LOGITS
    wg
    0.07
     BS
    0.07
     Access
    0.06
     đi
    0.06
    NotAllowed
    0.06
    /blob
    0.06
    021
    0.06
     Qgs
    0.06
     productName
    0.06
    _FILENAME
    0.06
    Act Density 0.000%

    No Known Activations