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

    Neuronpedia

    INDEX
    Explanations

    diagnostic tools

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    াস্ত
    0.45
    wallepics
    0.45
    ट्र
    0.45
    atoes
    0.45
    scientists
    0.44
    ules
    0.42
    ંત
    0.42
    osters
    0.42
     interracial
    0.42
    eg
    0.42
    POSITIVE LOGITS
     protease
    0.44
     codecs
    0.43
     bimodule
    0.43
     ghost
    0.42
     synapse
    0.40
     deno
    0.39
     peningkatan
    0.39
     grating
    0.39
     prez
    0.38
     Corr
    0.38
    Act Density 0.004%

    No Known Activations