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

    Neuronpedia

    INDEX
    Explanations

    back or Back

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ्रेंस
    0.42
    avacan
    0.42
    niest
    0.41
    eneuve
    0.41
    imal
    0.41
    pest
    0.41
    ላቸው
    0.41
    bona
    0.41
     saranam
    0.40
     réglementation
    0.40
    POSITIVE LOGITS
     back
    0.49
     Back
    0.48
     zurück
    0.45
     -->
    0.44
     ->
    0.41
    Back
    0.41
     gradient
    0.38
     *
    0.38
     _
    0.37
     gradients
    0.37
    Act Density 0.025%

    No Known Activations