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

    Neuronpedia

    INDEX
    Explanations

    following "a"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    {
    0.77
     selected
    0.70
    ுகிற
    0.69
    >
    0.69
    },
    0.69
     devenir
    0.69
    EP
    0.68
    IP
    0.66
    ある
    0.66
     foreseen
    0.66
    POSITIVE LOGITS
     Arkadaşlar
    0.93
    ᠰ
    0.92
    ه
    0.90
    áf
    0.87
    ଙ
    0.84
    ଖ
    0.83
    ékony
    0.82
     gerçek
    0.80
     Làm
    0.79
     Biswas
    0.79
    Act Density 0.000%

    No Known Activations