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

    Neuronpedia

    INDEX
    Explanations

    the, an

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (ver
    -0.07
     guru
    -0.07
     reservoir
    -0.07
    Range
    -0.06
    premium
    -0.06
     list
    -0.06
    .observable
    -0.06
    느
    -0.06
    �
    -0.06
     ประเทศ
    -0.06
    POSITIVE LOGITS
    젤
    0.07
    taş
    0.07
    _assigned
    0.07
    lerdi
    0.07
     našeho
    0.06
    均
    0.06
    prung
    0.06
     घटन
    0.06
    ioso
    0.06
    _SITE
    0.06
    Act Density 0.161%

    No Known Activations