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

    Neuronpedia

    INDEX
    Explanations

    promise

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cries
    -0.08
    <main
    -0.07
    (itr
    -0.07
    _boxes
    -0.07
     ăn
    -0.07
    逆转
    -0.06
     cyan
    -0.06
     mell
    -0.06
    𤫉
    -0.06
     nói
    -0.06
    POSITIVE LOGITS
     WHILE
    0.07
    nested
    0.07
    eldom
    0.07
    -bl
    0.06
    misión
    0.06
     Impl
    0.06
    pseudo
    0.06
    item
    0.06
    quam
    0.06
    (self
    0.06
    Act Density 0.006%

    No Known Activations