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

    Neuronpedia

    INDEX
    Explanations

    design

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    #plt
    -0.07
    čně
    -0.07
    ñas
    -0.06
    슈
    -0.06
     urgently
    -0.06
    ()(
    -0.06
     leider
    -0.06
     Swipe
    -0.06
     MainActivity
    -0.06
     prostituerade
    -0.06
    POSITIVE LOGITS
    」の
    0.06
    VERTEX
    0.06
     decoded
    0.06
     various
    0.06
     abdom
    0.06
     Principal
    0.06
     simpl
    0.06
     hintText
    0.06
     lex
    0.06
     Bart
    0.06
    Act Density 0.026%

    No Known Activations