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

    Neuronpedia

    INDEX
    Explanations

    words related to descriptions and context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     değişken
    0.47
     ajo
    0.43
     съем
    0.38
    नून
    0.38
    **)
    0.38
     вина
    0.38
    луу
    0.38
     değişt
    0.38
    vykor
    0.38
     oryg
    0.38
    POSITIVE LOGITS
     insulation
    0.39
    itación
    0.37
     validated
    0.37
     Diploma
    0.37
    这个问题
    0.37
     Recommended
    0.36
    烫
    0.36
     favored
    0.36
    Recommended
    0.36
     Janeiro
    0.35
    Act Density 0.000%

    No Known Activations