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

    Neuronpedia

    INDEX
    Explanations

    vibe check rating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ril
    0.33
     Neptune
    0.33
    chal
    0.33
     malignancy
    0.32
    বর্ধমান
    0.32
    achim
    0.32
    wendung
    0.31
    ම
    0.31
     Botan
    0.31
    wachung
    0.31
    POSITIVE LOGITS
     indicator
    0.54
     skala
    0.54
     indication
    0.52
     каждому
    0.52
     indicating
    0.51
     scale
    0.50
     subjective
    0.50
     subjekt
    0.50
     estimate
    0.49
     каждого
    0.49
    Act Density 0.024%

    No Known Activations