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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    icont
    -0.07
     내려
    -0.06
     gallon
    -0.06
     "(
    -0.06
    _rooms
    -0.06
    रत
    -0.06
    );?>↵
    -0.06
    “(
    -0.06
    trying
    -0.06
     Embedded
    -0.06
    POSITIVE LOGITS
    852
    0.08
    ância
    0.07
    prite
    0.06
    克
    0.06
     phot
    0.06
     watch
    0.06
     انگ
    0.06
     invitation
    0.06
    /tool
    0.06
    ock
    0.06
    Act Density 0.000%

    No Known Activations