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

    Neuronpedia

    INDEX
    Explanations

    you

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     becomes
    -0.06
    >//
    -0.06
    	items
    -0.06
     mistress
    -0.06
    Xd
    -0.06
    RowAtIndexPath
    -0.06
    เตอร
    -0.06
     beside
    -0.06
    912
    -0.06
     Sug
    -0.06
    POSITIVE LOGITS
     شرح
    0.07
    _RUN
    0.07
     ideology
    0.07
    _flat
    0.06
    unft
    0.06
     rukou
    0.06
     đội
    0.06
    �
    0.06
    冊
    0.06
    يج
    0.06
    Act Density 0.029%

    No Known Activations