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

    Neuronpedia

    INDEX
    Explanations

    prior to or nearing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    نك
    0.48
    Chapter
    0.46
    प
    0.46
    ็อก
    0.44
    ด
    0.44
    ]}
    0.44
    findOne
    0.44
     defaults
    0.44
     inquire
    0.43
    ме
    0.42
    POSITIVE LOGITS
    rahydro
    0.54
     août
    0.51
    ko
    0.50
    ertes
    0.50
    riu
    0.49
    ific
    0.49
     novembre
    0.48
    remeno
    0.48
     கூடிய
    0.47
    ura
    0.46
    Act Density 0.000%

    No Known Activations