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

    Neuronpedia

    INDEX
    Explanations

    environmental conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     구현
    0.52
     manuss
    0.52
    描写
    0.50
     値
    0.48
    !]
    0.48
     teknik
    0.47
    ourke
    0.47
     wobei
    0.46
    lysninger
    0.46
     χρή
    0.46
    POSITIVE LOGITS
    ້ນ
    0.50
    ញ
    0.49
    लावा
    0.48
    rocks
    0.48
    mıştı
    0.48
    ée
    0.47
     xref
    0.47
    िर
    0.46
    ulares
    0.46
    áu
    0.46
    Act Density 0.000%

    No Known Activations