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

    Neuronpedia

    INDEX
    Explanations

    beginning of queries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    0.86
     al
    0.82
     d
    0.81
     ge
    0.78
     (
    0.78
     ab
    0.78
     is
    0.77
     mes
    0.74
     neat
    0.74
     strictly
    0.74
    POSITIVE LOGITS
    푦
    1.22
    🧉
    1.18
    🥸
    1.18
    ítulos
    1.16
    apayati
    1.16
    导致
    1.15
    ivasena
    1.14
    Ꮡ
    1.14
    aniyam
    1.13
    owneri
    1.12
    Act Density 0.024%

    No Known Activations