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

    Neuronpedia

    INDEX
    Explanations

    above, top, down

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _than
    -0.07
    бом
    -0.07
     Asking
    -0.07
    Porn
    -0.07
    _logging
    -0.06
    .dd
    -0.06
     wildcard
    -0.06
    Country
    -0.06
    .cd
    -0.06
    icmp
    -0.06
    POSITIVE LOGITS
     повітря
    0.07
     并
    0.07
    -inter
    0.07
     Birch
    0.07
     fourn
    0.07
    Ї
    0.06
    [ind
    0.06
     nil
    0.06
     mysl
    0.06
     Assume
    0.06
    Act Density 0.066%

    No Known Activations