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

    Neuronpedia

    INDEX
    Explanations

    word parts and their continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    by
    0.49
     by
    0.46
    ado
    0.43
    for
    0.43
    ook
    0.42
    akes
    0.42
     понятия
    0.42
    ;
    0.42
    ager
    0.41
     docentes
    0.40
    POSITIVE LOGITS
     incrível
    0.60
     ಹಣ
    0.47
    啲
    0.47
     fırs
    0.46
     conquer
    0.45
     relic
    0.45
    assertArg
    0.45
    ᱣ
    0.45
     karst
    0.43
     counterfeit
    0.43
    Act Density 0.073%

    No Known Activations