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

    Neuronpedia

    INDEX
    Explanations

    they

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    809
    -0.07
     göster
    -0.06
     delete
    -0.06
    ştır
    -0.06
     نه
    -0.06
    	mv
    -0.06
    ToLower
    -0.06
     Athena
    -0.06
    _chars
    -0.06
     tame
    -0.06
    POSITIVE LOGITS
    AINER
    0.08
    ोल
    0.07
    ΟΛ
    0.07
    анг
    0.07
     melakukan
    0.07
    ↑
    0.07
     زیبا
    0.07
    ره
    0.07
    GridView
    0.06
    argon
    0.06
    Act Density 0.095%

    No Known Activations