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

    Neuronpedia

    INDEX
    Explanations

    potential and achievable outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     osób
    0.69
     berusia
    0.67
     osoby
    0.65
     معلومات
    0.64
    María
    0.64
     വിദ്യാ
    0.64
    ódio
    0.63
     정보
    0.62
     increí
    0.62
     informieren
    0.62
    POSITIVE LOGITS
     potential
    0.76
     possible
    0.70
     achievable
    0.67
     electrical
    0.66
     maximum
    0.66
     peak
    0.65
     economics
    0.64
     feasible
    0.63
     allowable
    0.63
     energy
    0.62
    Act Density 0.000%

    No Known Activations