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

    Neuronpedia

    INDEX
    Explanations

    .io

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    近く
    -0.08
    กำไร
    -0.08
    _SEG
    -0.07
     Kern
    -0.07
    _bm
    -0.07
     الشهر
    -0.07
     Vari
    -0.07
     мира
    -0.07
     sicher
    -0.07
    mana
    -0.06
    POSITIVE LOGITS
    ⤶
    0.07
    iced
    0.07
    ined
    0.07
    inged
    0.07
    옐
    0.06
     truck
    0.06
     rollers
    0.06
     resource
    0.06
    ----------</
    0.06
    ⛈
    0.06
    Act Density 0.003%

    No Known Activations