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

    Neuronpedia

    INDEX
    Explanations

    naive

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    i
    -0.56
     for
    -0.52
    y
    -0.51
     
    -0.50
     sp
    -0.48
     the
    -0.46
    s
    -0.46
     an
    -0.44
    pade
    -0.44
    dır
    -0.44
    POSITIVE LOGITS
     myſelf
    1.33
     Efq
    1.31
     Houſe
    1.28
     itſelf
    1.26
     Majefty
    1.24
     pleaſure
    1.24
     themſelves
    1.20
     Jefus
    1.20
     faſt
    1.20
     houſe
    1.20
    Act Density 0.060%

    No Known Activations