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

    Neuronpedia

    INDEX
    Explanations

    json, name, cdf, complete

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    وجد
    0.41
    Detectable
    0.40
    elevationMap
    0.40
    corper
    0.39
     الصور
    0.39
    ceria
    0.38
    uner
    0.38
     refiere
    0.38
     recom
    0.37
     検
    0.37
    POSITIVE LOGITS
     fight
    0.39
    ming
    0.38
    daq
    0.37
     Django
    0.35
    醤
    0.35
     Savoy
    0.35
     node
    0.35
    Fight
    0.34
     Babel
    0.34
     Nietzsche
    0.34
    Act Density 0.000%

    No Known Activations