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

    Neuronpedia

    INDEX
    Explanations

    defining a role for you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     skil
    0.70
     stick
    0.69
    нак
    0.67
     readily
    0.67
    additional
    0.66
     반드시
    0.66
     broken
    0.65
    Continue
    0.64
     sticking
    0.63
     accordingly
    0.63
    POSITIVE LOGITS
     Hace
    1.01
     hace
    0.89
     prestación
    0.87
     geology
    0.86
     bioquímica
    0.84
     gouvernement
    0.84
     acque
    0.83
     departamento
    0.83
     în
    0.82
     quieren
    0.82
    Act Density 0.344%

    No Known Activations