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

    Neuronpedia

    INDEX
    Explanations

    chemical compositions

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of material formulations or chemical substances—words referring to compositions, compounds, resins, etc.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _GROUPS
    -0.06
     ylim
    -0.06
     rows
    -0.06
    illegal
    -0.06
    PostMapping
    -0.06
    Invoker
    -0.06
     Kou
    -0.05
    bot
    -0.05
    _modifier
    -0.05
    　ノ
    -0.05
    POSITIVE LOGITS
    غ
    0.07
    ulpt
    0.07
     방송
    0.07
     Glob
    0.07
    '])){
    0.07
     usually
    0.06
     ؟
    0.06
     Roof
    0.06
     �
    0.06
    .volley
    0.06
    Act Density 0.035%

    No Known Activations