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

    Neuronpedia

    INDEX
    Explanations

    app design

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    站
    -0.07
     Stable
    -0.07
     Boy
    -0.07
     ingredients
    -0.06
     wart
    -0.06
    兹
    -0.06
    -expanded
    -0.06
    	Delete
    -0.06
    恶
    -0.06
    /fast
    -0.06
    POSITIVE LOGITS
    ืน
    0.06
    incipal
    0.06
    wo
    0.06
     corresponding
    0.06
    GT
    0.06
    enthal
    0.06
    726
    0.06
    Vote
    0.06
    _Pr
    0.06
     Volkswagen
    0.06
    Act Density 0.020%

    No Known Activations