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

    Neuronpedia

    INDEX
    Explanations

    names of brands and people

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gable
    0.43
    waste
    0.43
    simply
    0.39
    HLA
    0.38
    explore
    0.37
    nable
    0.37
    prüfung
    0.37
    ་་
    0.37
     explore
    0.36
    leading
    0.36
    POSITIVE LOGITS
     certain
    0.58
     Iraqi
    0.55
     Iraq
    0.55
    某些
    0.53
     Sudan
    0.51
     например
    0.49
     Saddam
    0.49
     notorious
    0.48
     tomatoes
    0.48
     Kashmir
    0.47
    Act Density 0.060%

    No Known Activations