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

    Neuronpedia

    INDEX
    Explanations

    Los

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Los
    -1.09
     los
    -1.05
    Los
    -0.98
     El
    -0.85
     (
    -0.79
     las
    -0.78
    ,
    -0.78
    El
    -0.77
     el
    -0.75
     in
    -0.75
    POSITIVE LOGITS
     myſelf
    1.70
     itſelf
    1.66
     themſelves
    1.56
     purpoſe
    1.53
     Monfieur
    1.50
     Efq
    1.48
     pleaſure
    1.48
    ſelves
    1.46
     Jefus
    1.46
     ſeveral
    1.46
    Act Density 1.656%

    No Known Activations