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

    Neuronpedia

    INDEX
    Explanations

    =

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     deleting
    -0.07
    种
    -0.06
     pods
    -0.06
     '\'
    -0.06
     irrational
    -0.06
     Duck
    -0.06
    _NOW
    -0.06
    banner
    -0.06
    +"&
    -0.06
    -functions
    -0.06
    POSITIVE LOGITS
     फ
    0.07
    ologic
    0.07
    jad
    0.06
    etas
    0.06
    .relative
    0.06
    aptor
    0.06
     seamlessly
    0.06
    anza
    0.06
    hf
    0.06
     newText
    0.06
    Act Density 0.064%

    No Known Activations