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

    Neuronpedia

    INDEX
    Explanations

    encourages outdoor, entirely dependent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ssia
    0.42
     মধুর
    0.41
    자들이
    0.39
    0.39
    Trailing
    0.38
     Tack
    0.37
     declarar
    0.35
    Duties
    0.35
     dichiar
    0.35
     razones
    0.35
    POSITIVE LOGITS
     strept
    0.43
     frequently
    0.42
     volts
    0.40
     cisplatin
    0.40
     frequentemente
    0.38
    чиго
    0.38
     whereabouts
    0.38
     officer
    0.37
    requently
    0.37
     sporty
    0.37
    Act Density 0.000%

    No Known Activations