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

    Neuronpedia

    INDEX
    Explanations

    boundary delimiters or code separation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     connus
    0.89
    策略
    0.89
    状况
    0.88
    现有
    0.82
    ifères
    0.81
     problèmes
    0.81
    會有
    0.80
    botones
    0.80
    谎
    0.80
    不
    0.79
    POSITIVE LOGITS
     Lim
    0.70
     alumna
    0.69
     arugula
    0.69
    ysis
    0.68
     extrema
    0.68
     Prepar
    0.68
     Papua
    0.67
     autopsy
    0.67
    a
    0.66
    d
    0.66
    Act Density 0.012%

    No Known Activations