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

    Neuronpedia

    INDEX
    Explanations

    claimed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     *)&
    -0.08
    -0.07
    -0.07
    -0.07
     altru
    -0.07
     ráp
    -0.07
     oranı
    -0.07
    -0.07
     práci
    -0.07
    -0.06
    POSITIVE LOGITS
     आत
    0.07
     Gluten
    0.07
     tom
    0.06
    bel
    0.06
    Equipment
    0.06
    apot
    0.06
     Equipment
    0.06
    ountain
    0.06
    -generic
    0.06
    販
    0.06
    Act Density 0.001%

    No Known Activations