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

    Neuronpedia

    INDEX
    Explanations

    numerical sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pesante
    0.81
     Session
    0.77
    แกรม
    0.74
     artistas
    0.74
    压力
    0.73
    acu
    0.72
     crebre
    0.71
     session
    0.71
    rograman
    0.70
     eerste
    0.70
    POSITIVE LOGITS
    Peace
    0.75
     peace
    0.68
    pdf
    0.67
     god
    0.66
    ข
    0.66
     Smiths
    0.66
    埂
    0.65
     Peace
    0.65
    inca
    0.64
     методи
    0.64
    Act Density 0.161%

    No Known Activations