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

    Neuronpedia

    INDEX
    Explanations

    Beginning of sentences/text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iler
    -0.07
    ider
    -0.07
    rido
    -0.06
     night
    -0.06
    _prog
    -0.06
    rm
    -0.06
     money
    -0.06
     katkı
    -0.06
    _position
    -0.06
    誉
    -0.06
    POSITIVE LOGITS
    %%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
    0.06
    ('')↵
    0.06
    书记
    0.06
    ']],
    0.06
    -most
    0.06
    ('../../
    0.06
    )<<
    0.06
    apult
    0.06
     SCIP
    0.06
    ,to
    0.06
    Act Density 0.220%

    No Known Activations