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

    Neuronpedia

    INDEX
    Explanations

    directions, how, before, item, something, a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     confid
    0.50
    Appointment
    0.49
     convenient
    0.46
     collectors
    0.46
     mentorship
    0.46
     comforting
    0.45
    appointment
    0.44
     appointment
    0.44
     Merry
    0.44
     confusing
    0.44
    POSITIVE LOGITS
    镑
    0.51
     ác
    0.50
     Encoder
    0.49
    犾
    0.49
     tm
    0.48
     灬
    0.48
     Evaluación
    0.47
     Análisis
    0.47
    ೋಗ
    0.47
     Energía
    0.46
    Act Density 0.000%

    No Known Activations