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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash

    This neuron never activates—it doesn’t respond to any tokens.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Templates
    -0.07
     reorder
    -0.07
    lesen
    -0.07
    stva
    -0.07
    itudes
    -0.06
     Collapse
    -0.06
    ptune
    -0.06
    -summary
    -0.06
    POCH
    -0.06
     reserve
    -0.06
    POSITIVE LOGITS
     Gab
    0.06
    _flags
    0.06
            
↵        
↵
    0.06
    سات
    0.06
            ↵        ↵
    0.05
            ↵
    0.05
    hai
    0.05
            
↵
    0.05
     Vib
    0.05
     Flem
    0.05
    Act Density 0.092%

    No Known Activations