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

    Neuronpedia

    INDEX
    Explanations

    authorisation and resizing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     عجیب
    0.39
    стрі
    0.38
    まれ
    0.37
     czek
    0.36
     متفاوت
    0.36
     görüntü
    0.36
     obfusc
    0.36
     dotnet
    0.35
    ระบบ
    0.35
     Terrorism
    0.35
    POSITIVE LOGITS
     authorised
    0.44
     authorise
    0.41
     manio
    0.40
    kker
    0.40
     authorized
    0.39
     authorize
    0.39
    žio
    0.38
    jų
    0.38
     ginh
    0.38
    ilig
    0.36
    Act Density 0.000%

    No Known Activations