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

    Neuronpedia

    INDEX
    Explanations

    math, code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ্�
    -0.07
    bbb
    -0.07
    atitis
    -0.07
    .bulk
    -0.07
     ruku
    -0.07
     Shelter
    -0.07
    CrLf
    -0.07
    /footer
    -0.07
    -yyyy
    -0.06
     Assad
    -0.06
    POSITIVE LOGITS
    مه
    0.07
    лению
    0.06
    EPS
    0.06
    ?</
    0.06
    fail
    0.06
    VEL
    0.05
     복
    0.05
     feminism
    0.05
    aksi
    0.05
    ITIONS
    0.05
    Act Density 0.016%

    No Known Activations