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

    Neuronpedia

    INDEX
    Explanations

    percentages/rates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kring
    0.39
     invari
    0.39
     ambi
    0.37
     Famous
    0.37
     Ambient
    0.37
     வாங்கி
    0.36
     निम्
    0.36
     తో
    0.36
    ถ่าย
    0.36
    periodic
    0.36
    POSITIVE LOGITS
     percentages
    0.40
     Bree
    0.40
    lwjglVersion
    0.39
     rates
    0.38
     percentage
    0.38
     recent
    0.38
    Rates
    0.38
     rø
    0.37
    ᴇ
    0.37
    }$&$
    0.36
    Act Density 0.000%

    No Known Activations