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

    Neuronpedia

    INDEX
    Explanations

    between

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Temple
    -0.07
    ョ
    -0.07
     Champion
    -0.06
     Hunts
    -0.06
    Lic
    -0.06
     Colony
    -0.06
     Taipei
    -0.06
    entai
    -0.06
    Ch
    -0.06
    ェ
    -0.06
    POSITIVE LOGITS
    />";↵
    0.08
    _train
    0.07
    450
    0.07
     ');↵
    0.07
    >').
    0.07
    querySelector
    0.06
    Tại
    0.06
     ePub
    0.06
    /right
    0.06
     inserting
    0.06
    Act Density 0.009%

    No Known Activations