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

    Neuronpedia

    INDEX
    Explanations

    Notifications and requests

    np_max-act · gemini-2.0-flash

    This neuron detects administrative or procedural language outlining how to request, apply for, or provide documentation for accommodations or support services.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Collapse
    -0.07
    ampion
    -0.06
    능
    -0.06
    	utils
    -0.06
    ional
    -0.06
    CHAN
    -0.06
     kd
    -0.05
    جوی
    -0.05
     cumshot
    -0.05
    fh
    -0.05
    POSITIVE LOGITS
    814
    0.07
     FirebaseAuth
    0.07
     Metallic
    0.06
    ницт
    0.06
     delim
    0.06
    nano
    0.06
     Civic
    0.06
     تص
    0.06
    (identifier
    0.06
    -expanded
    0.06
    Act Density 0.024%

    No Known Activations