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

    Neuronpedia

    INDEX
    Explanations

    two types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ahnya
    0.46
    weit
    0.41
    తిక
    0.41
    镓
    0.39
     Flexible
    0.38
     ಕಬ್ಬಿಣ
    0.37
     लची
    0.37
    uela
    0.37
     aște
    0.37
     liberar
    0.37
    POSITIVE LOGITS
     excursions
    0.45
     EOF
    0.45
     intense
    0.43
    ˄
    0.42
    Appointments
    0.40
     busier
    0.40
     appointments
    0.40
     intenso
    0.40
    EOF
    0.38
     notifications
    0.37
    Act Density 0.002%

    No Known Activations