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

    Neuronpedia

    INDEX
    Explanations

    name

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     utc
    -0.06
    ака
    -0.06
     औ
    -0.06
    utor
    -0.06
    ynı
    -0.06
    avn
    -0.06
     vulner
    -0.06
    ií
    -0.06
    .stock
    -0.06
    _Core
    -0.06
    POSITIVE LOGITS
    <Response
    0.07
    755
    0.06
    Spanish
    0.06
    原因
    0.06
     prm
    0.06
    Membership
    0.06
    SCR
    0.06
     trouver
    0.06
     thanked
    0.06
    <br
    0.06
    Act Density 0.121%

    No Known Activations