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

    Neuronpedia

    INDEX
    Explanations

    maintaining context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     negozi
    0.70
    iega
    0.69
     arbitr
    0.67
    Hej
    0.67
     вида
    0.65
    prova
    0.64
     AID
    0.63
     commonly
    0.63
     contracted
    0.63
     mercato
    0.62
    POSITIVE LOGITS
     Critique
    0.99
     lágrimas
    0.85
    ája
    0.81
    лый
    0.80
    ospital
    0.80
     critique
    0.77
    оны
    0.77
    ána
    0.75
    nál
    0.74
     kritik
    0.73
    Act Density 0.000%

    No Known Activations