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

    Neuronpedia

    INDEX
    Explanations

    Technical document context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ftagPool
    -0.80
     houſe
    -0.80
     виправивши
    -0.77
     NSCoder
    -0.76
     متعلقه
    -0.69
     Houſe
    -0.67
    posedge
    -0.66
     bezeichneter
    -0.66
     تضيفلها
    -0.65
    -0.65
    POSITIVE LOGITS
    ://$
    0.43
     [*]
    0.42
    olas
    0.42
     Michael
    0.41
     $
    0.39
     session
    0.38
    angi
    0.37
     Ser
    0.36
    ná
    0.35
     ang
    0.34
    Act Density 0.000%

    No Known Activations