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

    Neuronpedia

    INDEX
    Explanations

    dependency relations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     street
    0.56
     parlato
    0.49
    街
    0.48
     gyven
    0.47
     cidad
    0.45
     toman
    0.43
     gioco
    0.41
     remboursement
    0.41
     horsepower
    0.41
     ulic
    0.41
    POSITIVE LOGITS
    assignments
    0.44
     এরপর
    0.43
    Ṛ
    0.40
    Ǎ
    0.40
    ibs
    0.39
     उन्हें
    0.39
    ări
    0.39
     Саме
    0.38
    Electronics
    0.38
    stellungen
    0.38
    Act Density 0.014%

    No Known Activations