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

    Neuronpedia

    INDEX
    Explanations

    problems and issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ulfill
    0.69
    استشهاد
    0.61
    ޯ
    0.61
     ننوت
    0.60
    呸
    0.59
    더라도
    0.57
    uevo
    0.57
    ന്റ
    0.56
    yel
    0.55
    త్య
    0.55
    POSITIVE LOGITS
     problems
    5.81
     problem
    5.70
     Problem
    5.29
    problem
    5.29
     Problems
    5.29
     problema
    5.27
    Problem
    5.16
     problemas
    5.14
     problème
    5.11
    problems
    5.07
    Act Density 1.442%

    No Known Activations