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

    Neuronpedia

    INDEX
    Explanations

    Names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .With
    -0.07
    BER
    -0.07
    ERENCE
    -0.06
    .mark
    -0.06
     ενώ
    -0.06
    推薦
    -0.06
     unparalleled
    -0.06
    .generate
    -0.06
    ้าท
    -0.06
    .parentElement
    -0.06
    POSITIVE LOGITS
    article
    0.06
    なた
    0.06
    ायन
    0.06
    (txt
    0.06
    DDR
    0.06
    km
    0.06
     hãy
    0.06
    ="@
    0.05
    —I
    0.05
    ANGED
    0.05
    Act Density 0.132%

    No Known Activations