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

    Neuronpedia

    INDEX
    Explanations

    Germanic language suffixes and articles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     evidentiary
    0.56
     Biden
    0.54
     Austrian
    0.53
     Odisha
    0.52
     billionaire
    0.51
     Scots
    0.51
     joueur
    0.50
     이는
    0.49
     misdemeanor
    0.49
     prophetic
    0.49
    POSITIVE LOGITS
    ,
    0.59
    то
    0.57
     и
    0.57
    .
    0.55
    や
    0.55
    ските
    0.54
    на
    0.53
     на
    0.51
     و
    0.50
    م
    0.49
    Act Density 0.000%

    No Known Activations