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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     слад
    0.85
     seminal
    0.84
     perilous
    0.82
     invertir
    0.81
    േണ്ട
    0.79
     Erich
    0.79
    coding
    0.79
     cerrada
    0.79
    UpdateChoice
    0.78
     unimportant
    0.78
    POSITIVE LOGITS
     LOVE
    0.70
     love
    0.69
     value
    0.68
     admire
    0.67
     treasure
    0.65
    Value
    0.63
     trust
    0.63
     tình
    0.62
    CRR
    0.62
     वैल्यू
    0.61
    Act Density 0.094%

    No Known Activations