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

    Neuronpedia

    INDEX
    Explanations

    Names and places

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ro
    -0.83
     Sa
    -0.73
     Or
    -0.67
     Tr
    -0.65
     H
    -0.63
     I
    -0.61
     or
    -0.60
     Ho
    -0.60
     Bar
    -0.58
     P
    -0.57
    POSITIVE LOGITS
    ſelves
    1.10
     pleaſure
    1.10
    ſelf
    1.07
     Monfieur
    1.07
     myſelf
    1.05
     Majefty
    1.01
     purpoſe
    1.00
     ſmall
    1.00
     itſelf
    0.99
     cauſe
    0.97
    Act Density 0.156%

    No Known Activations