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

    Neuronpedia

    INDEX
    Explanations

    academic and university settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lifting
    0.42
    ael
    0.42
    astes
    0.40
    aye
    0.39
    elt
    0.39
     Juven
    0.39
    tenberg
    0.39
    erv
    0.38
     fantast
    0.38
     DeS
    0.38
    POSITIVE LOGITS
    ROR
    0.39
    سا
    0.38
    ScienceStudent
    0.38
    0.38
    ディ
    0.38
    гистра
    0.38
     साव
    0.37
    Med
    0.36
     epitaxial
    0.36
     EMB
    0.36
    Act Density 0.000%

    No Known Activations