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

    Neuronpedia

    INDEX
    Explanations

    a variety of short words or phrases that seem to be in the middle of a sentence, acting as punctuation

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     invests
    -0.67
     håller
    -0.67
    实现了
    -0.66
    saraba
    -0.66
     robić
    -0.65
    FunctionFlags
    -0.61
     DOING
    -0.61
     выполнять
    -0.61
    ोंने
    -0.61
    wrote
    -0.61
    POSITIVE LOGITS
     thrust
    0.50
    ритори
    0.49
     quot
    0.47
    lankton
    0.47
     hoist
    0.47
     fret
    0.47
     Courant
    0.45
     stash
    0.45
     intertw
    0.45
     demur
    0.45
    Act Density 2.648%

    No Known Activations