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

    Neuronpedia

    INDEX
    Explanations

    Research papers/articles/books

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    。お
    -0.07
     abruptly
    -0.07
     professionalism
    -0.06
    blind
    -0.06
    .Sound
    -0.06
     اهم
    -0.06
     Royal
    -0.06
    ikal
    -0.06
    Coins
    -0.06
    Transactional
    -0.06
    POSITIVE LOGITS
     getDate
    0.07
     manner
    0.06
    	BYTE
    0.06
     WE
    0.06
    віт
    0.06
    acas
    0.06
     onclick
    0.06
     gast
    0.06
     BUTTON
    0.06
     anthology
    0.06
    Act Density 0.009%

    No Known Activations