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

    Neuronpedia

    INDEX
    Explanations

    trojan horses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     slalom
    0.54
     zur
    0.50
    Ǘ
    0.49
     mision
    0.47
    Nueva
    0.47
     zum
    0.47
    ूहिक
    0.47
     Nept
    0.46
     zabezpie
    0.46
     magnon
    0.45
    POSITIVE LOGITS
    వ
    0.52
    στο
    0.48
    $.
    0.47
    $,
    0.46
    $$
    0.46
    5
    0.46
    sw
    0.45
    ме
    0.45
    сел
    0.45
    pm
    0.45
    Act Density 0.000%

    No Known Activations