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

    Neuronpedia

    INDEX
    Explanations

    Hep

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     itſelf
    -1.09
     myſelf
    -1.00
     themſelves
    -0.99
     ModelExpression
    -0.98
     himſelf
    -0.93
     Efq
    -0.89
     leſs
    -0.89
     becauſe
    -0.88
     raiſ
    -0.88
     faſt
    -0.87
    POSITIVE LOGITS
    an
    0.54
    en
    0.51
    al
    0.50
    e
    0.49
    ech
    0.47
     A
    0.47
     P
    0.46
    ed
    0.46
    principalTable
    0.44
    eta
    0.44
    Act Density 1.191%

    No Known Activations