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

    Neuronpedia

    INDEX
    Explanations

    AI model implications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Kre
    0.42
    Agenda
    0.42
    благо
    0.42
    agenda
    0.41
    pause
    0.41
    FEATURE
    0.40
     FEATURE
    0.39
    Florida
    0.39
    महा
    0.39
    せず
    0.38
    POSITIVE LOGITS
     ai
    0.39
     week
    0.38
     Mu
    0.36
     Guan
    0.36
     Ca
    0.36
     symmetrical
    0.36
     Transformer
    0.36
     '|')
    0.36
     Transformation
    0.35
     tin
    0.35
    Act Density 0.035%

    No Known Activations