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

    Neuronpedia

    INDEX
    Explanations

    academic degrees

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    anges
    0.38
    gwin
    0.38
     пунк
    0.38
    oscopes
    0.38
    dule
    0.37
    undle
    0.36
    ಮ್ಮೆ
    0.36
    ède
    0.35
     smartphones
    0.34
    eonium
    0.34
    POSITIVE LOGITS
     degree
    0.89
     Degree
    0.82
    Degree
    0.77
     degrees
    0.70
    degree
    0.69
     doctorate
    0.68
     степень
    0.68
     Degrees
    0.66
     degré
    0.63
     level
    0.60
    Act Density 0.008%

    No Known Activations