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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    逆
    -0.07
    нице
    -0.06
     Tage
    -0.06
     cuffs
    -0.06
     lasts
    -0.06
     unlikely
    -0.06
    TTY
    -0.06
     маль
    -0.06
    :$
    -0.06
    こんな
    -0.06
    POSITIVE LOGITS
    1
    0.08
    ١
    0.08
    １
    0.07
    १
    0.07
    /disc
    0.07
     πολι
    0.07
    _decl
    0.07
    <bool
    0.06
    901
    0.06
    insurance
    0.06
    Act Density 0.030%

    No Known Activations