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

    Neuronpedia

    INDEX
    Explanations

    wassup, wasm, wasD, was

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Итак
    0.35
     Teachers
    0.34
    eo
    0.34
    ôme
    0.34
     evolve
    0.32
    প্রতি
    0.32
    ዴ
    0.32
    osion
    0.32
    性的
    0.32
     proximate
    0.32
    POSITIVE LOGITS
     autrefois
    0.60
    wolves
    0.60
    htub
    0.53
     supposed
    0.51
    abi
    0.48
    hten
    0.47
    supp
    0.47
     einmal
    0.47
     dün
    0.47
     Васи
    0.45
    Act Density 0.010%

    No Known Activations