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

    Neuronpedia

    INDEX
    Explanations

    keywords, code, SMILES

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ాన్
    0.50
     alarms
    0.47
     sermon
    0.47
     minha
    0.47
     girlfriends
    0.46
     Bobby
    0.45
     ১৫০
    0.45
     greats
    0.44
    ెక్
    0.44
     diagnoses
    0.44
    POSITIVE LOGITS
    linear
    0.43
    akt
    0.42
    olí
    0.42
    approche
    0.41
    ítulo
    0.40
    nuclear
    0.40
    molecular
    0.39
    ý
    0.39
    †
    0.39
    phys
    0.39
    Act Density 0.016%

    No Known Activations