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

    Neuronpedia

    INDEX
    Explanations

    sample data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _over
    -0.08
     nto
    -0.08
     الحل
    -0.07
    �
    -0.07
    enti
    -0.07
     данный
    -0.07
     ctxt
    -0.07
    _tot
    -0.07
    Pizza
    -0.07
     ing
    -0.07
    POSITIVE LOGITS
    阅读全文
    0.07
    .StackTrace
    0.07
     różne
    0.07
    찍
    0.07
    .JLabel
    0.07
     Hawk
    0.07
    看你
    0.06
    ())->
    0.06
    .groupControl
    0.06
     |↵
    0.06
    Act Density 0.002%

    No Known Activations