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

    Neuronpedia

    INDEX
    Explanations

    #

    np_max-act · gemini-2.0-flash

    Explanation of neuron 4 behavior: the main thing this neuron does is find the leading exclamation marks used in Markdown image links (the “!” that begins `![](...)`).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     چرخ
    -0.07
    _GRP
    -0.06
    .offsetHeight
    -0.06
    zek
    -0.06
    eof
    -0.06
    .ff
    -0.06
     disproportion
    -0.06
    ],
    -0.06
     Mint
    -0.06
    	parent
    -0.06
    POSITIVE LOGITS
    |#
    0.08
     Nga
    0.06
    nick
    0.06
     outbreaks
    0.06
     richness
    0.06
     Malaysia
    0.06
     Herman
    0.06
     Vib
    0.06
     如
    0.06
     SOUND
    0.06
    Act Density 0.001%

    No Known Activations