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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lets
    -0.07
     वस
    -0.07
     restores
    -0.07
    芝
    -0.06
    swift
    -0.06
     جریان
    -0.06
     Ferry
    -0.06
    {↵↵
    -0.06
     limbs
    -0.06
    Js
    -0.06
    POSITIVE LOGITS
     Ay
    0.06
    fulness
    0.06
    番組
    0.06
    gpio
    0.06
    agrams
    0.06
     demonstrated
    0.06
    tyard
    0.06
    (defvar
    0.06
    kre
    0.06
    ıyla
    0.06
    Act Density 0.106%

    No Known Activations