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

    Neuronpedia

    INDEX
    Explanations

    tax deductibility

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     whats
    0.44
    栦
    0.41
    ኝ
    0.41
    <unused6>
    0.41
    犒
    0.41
    可能會
    0.40
    苯
    0.40
    fühl
    0.39
    ownicy
    0.39
     পর্যবেক্ষ
    0.38
    POSITIVE LOGITS
     English
    0.48
     H
    0.43
     Modules
    0.43
    ✦
    0.43
     Indigo
    0.42
     path
    0.41
     Prerequisites
    0.41
     Facilities
    0.41
     Experiments
    0.41
     sweep
    0.41
    Act Density 0.000%

    No Known Activations