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

    Neuronpedia

    INDEX
    Explanations

    the specific noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     három
    0.36
     mountain
    0.33
     octagon
    0.33
     propeller
    0.33
     squadron
    0.33
     lagoon
    0.32
     annoncé
    0.32
     picturesque
    0.32
    ちなみに
    0.32
     mountainous
    0.32
    POSITIVE LOGITS
     and
    0.33
     there
    0.33
    可以
    0.31
    ToBe
    0.31
     </>
    0.30
     you
    0.30
     !=
    0.30
    하지
    0.29
     จะ
    0.29
    จะ
    0.29
    Act Density 0.000%

    No Known Activations