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

    Neuronpedia

    INDEX
    Explanations

    Different languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iring
    -0.07
     enclosing
    -0.06
     ########
    -0.06
    raj
    -0.06
    *)↵↵
    -0.06
     पद
    -0.06
     planetary
    -0.06
    Present
    -0.06
    �
    -0.06
     dei
    -0.06
    POSITIVE LOGITS
     wraps
    0.07
     noticed
    0.06
    .Atomic
    0.06
     كرة
    0.06
     đảo
    0.06
    飛
    0.06
    接着
    0.06
    莉
    0.06
    .Hide
    0.06
    sometimes
    0.06
    Act Density 0.087%

    No Known Activations