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

    Neuronpedia

    INDEX
    Explanations

    Equality

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reversing
    -0.07
    ेन
    -0.06
     xls
    -0.06
     flipping
    -0.06
     Buff
    -0.06
     synchronization
    -0.06
     amazed
    -0.06
     Bentley
    -0.06
     wines
    -0.06
     assertions
    -0.06
    POSITIVE LOGITS
     perpetrated
    0.08
    isdigit
    0.07
     prostitu
    0.06
    '''
↵
    0.06
     propTypes
    0.06
    经营
    0.06
    fillType
    0.06
    (__('
    0.06
     Nẵng
    0.06
     těla
    0.06
    Act Density 0.004%

    No Known Activations