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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash

    The neuron activates on CamelCase identifiers—i.e. Java class or type names.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    �
    -0.08
     ration
    -0.07
    ardım
    -0.06
     angels
    -0.06
     tý
    -0.06
     vacancy
    -0.06
    ?!↵↵
    -0.06
     mosquitoes
    -0.06
    ΟΓ
    -0.06
     treaty
    -0.06
    POSITIVE LOGITS
    _al
    0.07
    [%
    0.07
    0.07
    .master
    0.07
    ์)
    0.07
    edited
    0.07
     добав
    0.06
    当前
    0.06
    �
    0.06
    explained
    0.06
    Act Density 0.003%

    No Known Activations