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

    Neuronpedia

    INDEX
    Explanations

    phone model suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     desktops
    0.44
     webinars
    0.43
     desktop
    0.43
    এইচ
    0.41
     stomp
    0.41
     hoses
    0.40
    定制
    0.40
     implant
    0.39
     processors
    0.39
    넘
    0.39
    POSITIVE LOGITS
    cett
    0.40
    aniy
    0.40
    attaa
    0.38
    arte
    0.38
    ogly
    0.37
     मोठ्या
    0.37
    rent
    0.37
    काय
    0.37
    ettre
    0.37
    zik
    0.37
    Act Density 0.010%

    No Known Activations