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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     υπο
    -0.07
     xương
    -0.07
    olley
    -0.06
    .ro
    -0.06
     وج
    -0.06
     đau
    -0.06
     Verizon
    -0.06
    _cou
    -0.06
     Cyber
    -0.06
    Fonts
    -0.06
    POSITIVE LOGITS
    :class
    0.07
     stringByAppendingString
    0.07
    <|end_of_text|>
    0.06
     mạnh
    0.06
     speeds
    0.06
    etermined
    0.06
    thermal
    0.06
    ,SIGNAL
    0.06
     исключ
    0.06
    ャ
    0.06
    Act Density 0.044%

    No Known Activations