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

    Neuronpedia

    INDEX
    Explanations

    offers and packages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    िली
    0.42
     کمپنیوں
    0.41
    ciju
    0.39
    ('${
    0.39
    odil
    0.37
    utherford
    0.37
    miller
    0.37
    érico
    0.37
     Poch
    0.37
     tarihinde
    0.37
    POSITIVE LOGITS
     plane
    0.50
     Plane
    0.43
     max
    0.42
     PLANE
    0.42
     spectra
    0.40
     regular
    0.40
     planes
    0.39
     >
    0.39
     meteor
    0.39
     Bridal
    0.39
    Act Density 0.002%

    No Known Activations