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

    Neuronpedia

    INDEX
    Explanations

    into/in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     отмеч
    -0.07
    uib
    -0.07
    补
    -0.06
     Rob
    -0.06
    ō
    -0.06
    atak
    -0.06
    rians
    -0.06
     Jiang
    -0.06
     sampling
    -0.06
     darüber
    -0.06
    POSITIVE LOGITS
    iking
    0.07
     passphrase
    0.07
     INITIAL
    0.06
     intptr
    0.06
     Arbitrary
    0.06
    plate
    0.06
     councillor
    0.06
     кис
    0.06
    kbd
    0.06
    throws
    0.06
    Act Density 0.013%

    No Known Activations