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

    Neuronpedia

    INDEX
    Explanations

    equals sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     startling
    -0.07
    ола
    -0.07
     Gospel
    -0.07
     Conservation
    -0.06
    "c
    -0.06
     sleek
    -0.06
     dokument
    -0.06
     Алекс
    -0.06
    geben
    -0.06
    ngen
    -0.06
    POSITIVE LOGITS
    (nextProps
    0.07
    oğu
    0.07
    nth
    0.06
    addr
    0.06
    harma
    0.06
     bude
    0.06
    ickerView
    0.06
     ers
    0.06
    PTR
    0.06
     proved
    0.06
    Act Density 0.006%

    No Known Activations