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

    Neuronpedia

    INDEX
    Explanations

    real world

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rés
    0.89
    설
    0.75
     bidang
    0.74
     массы
    0.74
     Ultimate
    0.73
    暉
    0.72
    Declare
    0.71
     Best
    0.70
    less
    0.70
    JLabel
    0.68
    POSITIVE LOGITS
     estate
    1.47
    istically
    1.33
     Estate
    1.24
    estate
    1.18
    igning
    1.16
    Estate
    1.16
    সম্মত
    1.05
     world
    1.03
    politik
    1.03
    ISTIC
    1.03
    Act Density 0.140%

    No Known Activations