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

    Neuronpedia

    INDEX
    Explanations

    passed, failed, miss, annual

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    прия
    0.58
    ول
    0.49
    丈
    0.48
    भ
    0.47
    करी
    0.46
    也在
    0.46
    粨
    0.45
    あげ
    0.45
    وات
    0.44
     आशा
    0.44
    POSITIVE LOGITS
     rib
    0.56
     cantar
    0.54
     compra
    0.54
     wood
    0.52
     riff
    0.52
     même
    0.51
    fed
    0.51
     monstrous
    0.51
     bubble
    0.50
     dég
    0.50
    Act Density 0.000%

    No Known Activations