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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ацию
    -0.07
    トラブル
    -0.07
    dispatch
    -0.07
    层层
    -0.07
    试探
    -0.07
    phins
    -0.07
    Reached
    -0.06
    chsel
    -0.06
    ContentPane
    -0.06
    沅
    -0.06
    POSITIVE LOGITS
    0.07
     אוהבים
    0.07
     printers
    0.07
    없
    0.07
    ]&
    0.06
     markings
    0.06
     YORK
    0.06
     />';↵
    0.06
    不在
    0.06
     nov
    0.06
    Act Density 0.001%

    No Known Activations