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

    Neuronpedia

    INDEX
    Explanations

    describing manner or quality

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    lify
    0.75
     Allowance
    0.73
     Stabilization
    0.73
    પણે
    0.70
    嵓
    0.68
     verso
    0.67
    ètement
    0.67
    orylation
    0.67
    cially
    0.66
    luoromethyl
    0.66
    POSITIVE LOGITS
    进行的
    0.93
    做的
    0.83
     occurring
    0.82
    生成的
    0.81
     ያሉ
    0.77
    写的
    0.76
     occuring
    0.76
    製の
    0.76
     schöne
    0.75
    发布的
    0.73
    Act Density 0.265%

    No Known Activations