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

    Neuronpedia

    INDEX
    Explanations

    list

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _bp
    -0.08
    fang
    -0.07
    _PRI
    -0.06
    eus
    -0.06
     کیلومتر
    -0.06
    @
    -0.06
    venient
    -0.06
     石
    -0.06
     Hills
    -0.06
    оро
    -0.06
    POSITIVE LOGITS
     synth
    0.06
     rall
    0.06
     attain
    0.06
     millet
    0.06
    DXVECTOR
    0.06
    得
    0.06
    Mot
    0.06
     evac
    0.06
    (seq
    0.06
    ention
    0.06
    Act Density 0.001%

    No Known Activations