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

    Neuronpedia

    INDEX
    Explanations

    logs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    jest
    -0.07
     Tet
    -0.07
    zes
    -0.06
    シャル
    -0.06
    	start
    -0.06
     Evropy
    -0.06
    istrovství
    -0.06
    pants
    -0.06
    anyak
    -0.06
    547
    -0.06
    POSITIVE LOGITS
     getS
    0.06
    dhcp
    0.06
     NSLocalizedString
    0.06
    .vertex
    0.06
     toJSON
    0.06
     wrestling
    0.06
                                    ↵
    0.06
     trúc
    0.06
    属性
    0.06
    Convertible
    0.06
    Act Density 0.009%

    No Known Activations