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

    Neuronpedia

    INDEX
    Explanations

    research methods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     post
    -0.07
    ция
    -0.06
    ̣c
    -0.06
    AR
    -0.06
    '''
↵
    -0.06
    OK
    -0.06
     GridLayout
    -0.06
    Vote
    -0.06
     priests
    -0.06
     kit
    -0.06
    POSITIVE LOGITS
    ,DB
    0.07
     Animated
    0.07
    toBeInTheDocument
    0.07
    于
    0.06
     ऑनल
    0.06
     temptation
    0.06
    чень
    0.06
    podob
    0.06
    於
    0.06
    .getRandom
    0.06
    Act Density 0.035%

    No Known Activations