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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    数据
    -0.07
    ordinal
    -0.06
    地区
    -0.06
     словами
    -0.06
    ॉर
    -0.06
     Zoo
    -0.06
     poner
    -0.06
    	resource
    -0.06
     cherry
    -0.05
    variables
    -0.05
    POSITIVE LOGITS
    .getMap
    0.07
    KNOWN
    0.07
    Left
    0.07
    ATOM
    0.07
    ура
    0.07
    AJ
    0.07
    قام
    0.07
     freshmen
    0.06
    tığını
    0.06
    -Nov
    0.06
    Act Density 0.163%

    No Known Activations