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

    Neuronpedia

    INDEX
    Explanations

    file

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     فى
    -0.07
     Fox
    -0.07
    acao
    -0.07
     POW
    -0.07
    ответ
    -0.07
    	sw
    -0.07
    (hwnd
    -0.07
     eldest
    -0.06
    (ctx
    -0.06
     бум
    -0.06
    POSITIVE LOGITS
     Initialized
    0.07
    严重的
    0.07
    更高的
    0.07
    多い
    0.07
    ùng
    0.07
    _SMS
    0.07
    Telefono
    0.07
    stanbul
    0.07
     dân
    0.07
     succes
    0.06
    Act Density 0.057%

    No Known Activations