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

    Neuronpedia

    INDEX
    Explanations

    clear confirmation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    is
    0.49
    tham
    0.49
    ig
    0.48
    ):
    0.46
    reys
    0.46
    et
    0.45
     pater
    0.44
    ဒ
    0.44
     correlation
    0.44
    atian
    0.44
    POSITIVE LOGITS
    ﻹ
    0.49
    ποί
    0.46
    治疗
    0.46
    生活的
    0.46
    toadd
    0.46
    నాన్ని
    0.45
    理论
    0.45
     extensión
    0.45
    ંપની
    0.45
     terapé
    0.45
    Act Density 0.000%

    No Known Activations