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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash

    The neuron detects named entities that serve as titles of tools, guidelines, programs, or section headings in scientific or technical documents.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    signal
    -0.06
    ponge
    -0.06
    Anthony
    -0.06
     pamph
    -0.06
     warrior
    -0.06
    ovol
    -0.06
     Chern
    -0.06
    ange
    -0.06
     marc
    -0.06
    kır
    -0.06
    POSITIVE LOGITS
    */)
    0.07
     "),↵
    0.07
    ]}
    0.07
    ा.↵
    0.06
     �
    0.06
     %}↵
    0.06
    圭
    0.06
    odynamics
    0.06
    	email
    0.06
     галузі
    0.06
    Act Density 0.055%

    No Known Activations