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

    Neuronpedia

    INDEX
    Explanations

    color names in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Logging
    0.40
     Messina
    0.40
     Immunol
    0.38
     Infirm
    0.38
    āta
    0.38
    ètent
    0.37
     режими
    0.35
    isalpha
    0.35
     الممل
    0.35
    يں
    0.35
    POSITIVE LOGITS
    rocess
    0.40
    ollow
    0.37
    varian
    0.37
     stup
    0.36
     FINE
    0.36
    white
    0.36
    ၻ
    0.36
     hollow
    0.35
     العملية
    0.35
    quality
    0.35
    Act Density 0.003%

    No Known Activations