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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /buttons
    -0.07
     rocker
    -0.07
    Lo
    -0.07
    ação
    -0.07
     پرد
    -0.07
    وس
    -0.07
    ываются
    -0.07
    	Map
    -0.07
     snadno
    -0.06
    	mock
    -0.06
    POSITIVE LOGITS
     maintaining
    0.07
    ЎыџN
    0.06
     alignSelf
    0.06
    .setOutput
    0.06
    inati
    0.06
    trecht
    0.06
     gunfire
    0.06
    (&:
    0.06
    リカ
    0.06
     Asphalt
    0.05
    Act Density 0.045%

    No Known Activations