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

    Neuronpedia

    INDEX
    Explanations

    fibonacci and factorial base cases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     screwed
    0.55
    ר
    0.55
     dniu
    0.54
     перво
    0.54
     quenched
    0.53
     goof
    0.53
     хотят
    0.52
     inclement
    0.52
     идут
    0.52
     днів
    0.52
    POSITIVE LOGITS
    0
    0.84
    ️⃣
    0.72
    <0x80>
    0.62
    as
    0.55
    tg
    0.52
    ád
    0.51
    at
    0.49
    istische
    0.47
    ns
    0.47
    atangan
    0.47
    Act Density 0.029%

    No Known Activations