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

    Neuronpedia

    INDEX
    Explanations

    words related to scales and measurement

    oai_token-act-pair · gemini-2.0-flash

    close or low

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     
    -0.82
    ,
    -0.78
      
    -0.75
     in
    -0.71
     I
    -0.71
     is
    -0.68
     the
    -0.67
    ↵↵
    -0.66
     a
    -0.66
     an
    -0.64
    POSITIVE LOGITS
    twimg
    1.30
    rungsseite
    1.22
     cherchés
    1.17
     doubtnut
    1.14
     snippetHide
    1.14
    NUMX
    1.12
    GEBURTSDATUM
    1.09
     дописавши
    1.07
     ―――――
    1.06
    SequentialGroup
    1.05
    Act Density 0.246%

    No Known Activations