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

    Neuronpedia

    INDEX
    Explanations

    dollar amounts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tu
    -0.07
    Pop
    -0.07
     खबर
    -0.07
    온
    -0.07
     weak
    -0.06
     문서
    -0.06
     untuk
    -0.06
    amik
    -0.06
    éro
    -0.06
    arov
    -0.06
    POSITIVE LOGITS
     MCU
    0.07
    urchase
    0.07
    =tf
    0.07
     якого
    0.07
    _CUR
    0.06
    (contents
    0.06
     psychic
    0.06
    '\
    0.06
     discomfort
    0.06
    .Regular
    0.06
    Act Density 0.010%

    No Known Activations