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

    Neuronpedia

    INDEX
    Explanations

    positive descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ſeveral
    -1.16
     pleaſure
    -1.13
     purpoſe
    -1.10
     Jefus
    -1.09
     ſmall
    -1.06
     Efq
    -1.05
     ſtate
    -1.04
     beſt
    -1.02
     ſen
    -1.02
     uſe
    -1.00
    POSITIVE LOGITS
     an
    0.50
     des
    0.49
     c
    0.46
    GEBURTSDATUM
    0.44
     in
    0.43
    qu
    0.42
     on
    0.39
     against
    0.38
     this
    0.38
     de
    0.37
    Act Density 0.341%

    No Known Activations