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

    Neuronpedia

    INDEX
    Explanations

    phone numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cream
    0.39
    haj
    0.37
    骖
    0.37
    tere
    0.36
    ্যারি
    0.36
     Terry
    0.36
    Terry
    0.36
    walker
    0.35
    polarity
    0.35
    稞
    0.35
    POSITIVE LOGITS
    $("
    0.37
     Shutterstock
    0.37
     segment
    0.36
     Roads
    0.35
    shutdown
    0.35
    ствен
    0.35
    usional
    0.34
     Legit
    0.34
     republic
    0.34
     Kotor
    0.34
    Act Density 0.003%

    No Known Activations