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

    Neuronpedia

    INDEX
    Explanations

    vitality and life

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    იდ
    0.74
    ള
    0.71
    iffer
    0.68
    atively
    0.68
    arif
    0.67
    ~\
    0.66
    CAL
    0.66
    Fcn
    0.66
    ጨማሪ
    0.66
     económ
    0.65
    POSITIVE LOGITS
     revital
    1.03
     l
    0.98
     y
    0.96
     i
    0.95
    на
    0.91
    р
    0.91
     o
    0.90
     in
    0.88
     alive
    0.88
     a
    0.87
    Act Density 0.043%

    No Known Activations