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

    Neuronpedia

    INDEX
    Explanations

    res

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Google
    -0.07
     Guaranteed
    -0.06
    uman
    -0.06
    	client
    -0.06
    .").
    -0.06
    .Buffer
    -0.06
     alive
    -0.06
     consuming
    -0.06
    _addresses
    -0.06
    üc
    -0.06
    POSITIVE LOGITS
    _MISS
    0.08
    =batch
    0.07
     [(
    0.06
     Webseite
    0.06
     ομά
    0.06
    
    0.06
     potvr
    0.06
     нами
    0.06
     &[
    0.06
     perv
    0.06
    Act Density 0.099%

    No Known Activations