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

    Neuronpedia

    INDEX
    Explanations

    assume role

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     poisons
    0.45
     sutures
    0.37
     disinfectant
    0.36
    mutate
    0.34
     mushrooms
    0.34
     poison
    0.34
     poisoning
    0.34
    പ്പോ
    0.33
    bullets
    0.33
    asthenia
    0.33
    POSITIVE LOGITS
    સો
    0.38
     guad
    0.38
    边的
    0.37
    产生
    0.36
     đơn
    0.36
     Grab
    0.34
     દ
    0.34
     স্বপ
    0.34
     управ
    0.34
     създа
    0.34
    Act Density 0.001%

    No Known Activations