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

    Neuronpedia

    INDEX
    Explanations

    Community

    np_max-act · gemini-2.0-flash

    This neuron activates on words used as section headings or prominent labels (e.g. titles, feature names, or other header-style tokens) in the document.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    EFF
    -0.07
    )||(
    -0.06
    Dto
    -0.06
    IPHER
    -0.06
     ARISING
    -0.06
     之
    -0.06
     IMP
    -0.06
     tougher
    -0.06
     ATT
    -0.06
    .Status
    -0.06
    POSITIVE LOGITS
    �에
    0.07
     Listener
    0.06
    Sections
    0.06
    =settings
    0.06
     defining
    0.06
    states
    0.06
     ficken
    0.06
    .getSharedPreferences
    0.06
    (World
    0.06
    PasswordField
    0.06
    Act Density 0.157%

    No Known Activations