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

    Neuronpedia

    INDEX
    Explanations

    Approval/Confirmation

    np_max-act · gemini-2.0-flash

    This neuron detects words and phrases that signal conditional or hypothetical statements about possible or future outcomes (e.g. “if,” “would,” “passed,” “approved,” “adopted,” “confirmed”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    .stats
    -0.07
     SERVICE
    -0.07
     Algebra
    -0.07
    Safety
    -0.07
    ROLLER
    -0.07
     Admiral
    -0.06
    aring
    -0.06
    -headed
    -0.06
    ový
    -0.06
     mechanics
    -0.06
    POSITIVE LOGITS
     thous
    0.07
     때문에
    0.06
     anom
    0.06
     �
    0.06
    "/>
↵
    0.06
    .sendRedirect
    0.06
     useStyles
    0.06
    _hresult
    0.06
     eso
    0.06
     Venue
    0.06
    Act Density 0.017%

    No Known Activations