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

    Neuronpedia

    INDEX
    Explanations

    code, technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     “
    -0.77
     ‘
    -0.71
     '
    -0.69
     "
    -0.68
     di
    -0.66
     «
    -0.65
     des
    -0.64
    …
    -0.63
     que
    -0.62
     y
    -0.61
    POSITIVE LOGITS
     myſelf
    1.64
     itſelf
    1.52
     purpoſe
    1.47
     themſelves
    1.45
     Efq
    1.42
     raiſ
    1.38
     Jefus
    1.37
     Monfieur
    1.36
     fubject
    1.34
     poffible
    1.32
    Act Density 1.189%

    No Known Activations