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

    Neuronpedia

    INDEX
    Explanations

    Main

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     commitment
    -0.08
     огранич
    -0.07
     explanatory
    -0.07
    ありがとう
    -0.07
    mys
    -0.07
    けて
    -0.06
     �
    -0.06
    واع
    -0.06
    fh
    -0.06
    OP
    -0.06
    POSITIVE LOGITS
     muted
    0.07
    ﾍ
    0.06
    %);↵
    0.06
     města
    0.06
     Tarif
    0.06
    )reader
    0.06
     packageName
    0.06
    536
    0.06
    _yellow
    0.06
    assin
    0.06
    Act Density 0.000%

    No Known Activations