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

    Neuronpedia

    INDEX
    Explanations

    all

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ebo
    -0.07
    Owned
    -0.07
     Wikip
    -0.07
     СРСР
    -0.06
     diagnosed
    -0.06
     diversos
    -0.06
     includ
    -0.06
    ovaných
    -0.06
     Daw
    -0.06
     paraph
    -0.06
    POSITIVE LOGITS
    ้ย
    0.07
    cılık
    0.06
    нів
    0.06
     rake
    0.06
    ěji
    0.06
     gratuites
    0.06
    ิง
    0.06
    ablytyped
    0.06
     �
    0.06
    is
    0.06
    Act Density 0.004%

    No Known Activations