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

    Neuronpedia

    INDEX
    Explanations

    in search of lost time

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     бизнес
    0.53
     estándares
    0.50
    шли
    0.50
     старосног
    0.49
     detección
    0.48
     obviamente
    0.46
     британ
    0.46
     Currie
    0.45
     темати
    0.45
     kapsamında
    0.45
    POSITIVE LOGITS
    Adorable
    0.61
     insensible
    0.56
     stupe
    0.56
     quinquina
    0.54
     quelquefois
    0.54
    adorable
    0.54
     despot
    0.54
     palpit
    0.53
     Messieurs
    0.53
     savages
    0.52
    Act Density 0.004%

    No Known Activations