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

    Neuronpedia

    INDEX
    Explanations

    formatting and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     greeting
    0.71
     greetings
    0.70
     असून
    0.67
     Raz
    0.65
    acruz
    0.64
     Um
    0.63
     Ras
    0.63
    brellas
    0.63
     rotors
    0.63
     hereunder
    0.62
    POSITIVE LOGITS
    |
    1.10
    |$
    1.05
     |
    0.91
    ||
    0.86
    |$.
    0.84
    |}{\
    0.81
    }|
    0.79
    |$,
    0.78
    _|
    0.77
    Mid
    0.76
    Act Density 0.024%

    No Known Activations