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

    Neuronpedia

    INDEX
    Explanations

    adapting size

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _SYS
    -0.08
    強
    -0.08
     Suffolk
    -0.07
    强
    -0.07
    荒
    -0.07
     Mental
    -0.07
     betray
    -0.07
     dividido
    -0.07
    ुल
    -0.07
    Mental
    -0.07
    POSITIVE LOGITS
     dynamically
    0.11
    -natural
    0.10
     naturally
    0.10
     déterminer
    0.09
     આધાર
    0.09
     individualized
    0.09
     unpredictable
    0.09
     adapting
    0.09
     प्राकृतिक
    0.08
     natural
    0.08
    Act Density 0.025%

    No Known Activations