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

    Neuronpedia

    INDEX
    Explanations

    PHP code and templating constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.42
     anhyd
    0.41
     ампли
    0.41
     membrana
    0.40
    โร
    0.40
    ὤ
    0.40
     hepat
    0.39
     Melville
    0.39
     lésions
    0.39
    า
    0.39
    POSITIVE LOGITS
    if
    0.63
     }
    0.55
    ↵
    0.53
     isset
    0.52
     if
    0.51
    []}
    0.50
    foreach
    0.49
    emit
    0.47
     emits
    0.47
    }}"
    0.46
    Act Density 0.024%

    No Known Activations