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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tf
    -0.07
     kw
    -0.06
     bj
    -0.06
     "...
    -0.06
    _tokenize
    -0.06
    /DTD
    -0.06
    ِك
    -0.06
    セ
    -0.06
    Signal
    -0.06
     demonstrate
    -0.05
    POSITIVE LOGITS
     actu
    0.08
    .tcp
    0.07
     등록
    0.07
    갔다
    0.07
    ición
    0.07
    орони
    0.06
    uchos
    0.06
    ύν
    0.06
    卫生
    0.06
    δρα
    0.06
    Act Density 0.000%

    No Known Activations