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

    Neuronpedia

    INDEX
    Explanations

    email addresses and info

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    إنجليزية
    0.74
    டியோ
    0.67
     Nası
    0.66
     байгаа
    0.66
    nee
    0.65
    MessageType
    0.64
    пель
    0.62
    ível
    0.62
    кі
    0.62
    agonal
    0.62
    POSITIVE LOGITS
     info
    1.47
    info
    1.46
     Info
    1.31
     INFO
    1.17
    Info
    1.10
    INFO
    1.06
     hello
    1.05
     admin
    1.01
     informazioni
    1.00
     maria
    0.99
    Act Density 0.142%

    No Known Activations