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

    Neuronpedia

    INDEX
    Explanations

    mathematical texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     disdain
    -0.06
     granny
    -0.06
     jumped
    -0.06
    Bell
    -0.06
    ename
    -0.06
    Arn
    -0.06
     service
    -0.06
     Osaka
    -0.06
    CAR
    -0.06
    -neutral
    -0.06
    POSITIVE LOGITS
    .catalog
    0.06
    min
    0.06
    '''
↵
    0.06
    	ap
    0.06
    _prom
    0.06
    _PERSON
    0.06
     rims
    0.06
     refinery
    0.06
    district
    0.06
    manufact
    0.06
    Act Density 0.012%

    No Known Activations