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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    GEBURTSDATUM
    -0.75
    Autoritní
    -0.71
     Roskov
    -0.63
    AccessLevel
    -0.53
    setVerticalGroup
    -0.53
    IsMutable
    -0.53
     autorytatywna
    -0.51
     مواليد
    -0.51
    oa̍t
    -0.50
    ReusableCell
    -0.50
    POSITIVE LOGITS
     Testa
    0.57
    eschou
    0.51
    nem
    0.51
     ModelAndView
    0.50
     recognizing
    0.49
     Jub
    0.49
     Италијани
    0.49
    省市镇
    0.48
    外的
    0.48
     Do
    0.48
    Act Density 0.001%

    No Known Activations