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

    Neuronpedia

    INDEX
    Explanations

    as

    np_max-act · gemini-2.0-flash

    The neuron activates on decimal numeric values (floating-point measurements) in technical scientific text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     CFR
    -0.06
     requirement
    -0.06
    _blocks
    -0.06
     dysfunctional
    -0.06
    uges
    -0.06
     Setup
    -0.06
    _AUTH
    -0.06
    quired
    -0.06
     balloons
    -0.06
    /Login
    -0.06
    POSITIVE LOGITS
     لباس
    0.07
        
↵    
↵
    0.06
     coerce
    0.06
    ↵   ↵
    0.06
     neighbourhood
    0.06
     국가
    0.06
    (const
    0.06
    ??↵↵
    0.06
     orth
    0.06
    дается
    0.06
    Act Density 0.031%

    No Known Activations