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

    Neuronpedia

    INDEX
    Explanations

    Abu Dhabi

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    е
    0.75
    atil
    0.71
    0.66
    ilibrium
    0.66
    annya
    0.65
     effecting
    0.65
    adients
    0.64
    اء
    0.64
    cribable
    0.63
    "
    0.63
    POSITIVE LOGITS
    وي
    0.93
     كان
    0.88
     Saúde
    0.86
    PatientR
    0.85
     saúde
    0.82
    1
    0.82
     أبو
    0.79
     douze
    0.78
    isRequired
    0.77
    োক
    0.76
    Act Density 0.003%

    No Known Activations