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

    Neuronpedia

    INDEX
    Explanations

    sure by definition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     boutiques
    0.53
     trains
    0.49
    ільки
    0.48
     faucets
    0.47
     guitars
    0.47
     zespo
    0.47
    /**/*.
    0.46
     sixties
    0.46
     collaborations
    0.45
     चार्ट
    0.45
    POSITIVE LOGITS
    sur
    0.47
     sür
    0.42
    apse
    0.42
    ні
    0.42
    oward
    0.42
    කා
    0.41
    fel
    0.40
    surfing
    0.40
    ని
    0.40
    Fel
    0.40
    Act Density 0.000%

    No Known Activations