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

    Neuronpedia

    INDEX
    Explanations

    you know

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cancelar
    0.95
     reciprocal
    0.92
     racers
    0.91
     vacations
    0.89
     dogs
    0.87
    rantes
    0.87
     plumbers
    0.87
     smaller
    0.87
     собак
    0.86
     clients
    0.86
    POSITIVE LOGITS
     êtes
    0.93
     are
    0.91
    E
    0.87
    eight
    0.85
     نے
    0.85
    FL
    0.84
    C
    0.84
    CH
    0.82
     cannot
    0.82
    Mong
    0.81
    Act Density 0.021%

    No Known Activations