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

    Neuronpedia

    INDEX
    Explanations

    exist

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     taped
    -0.07
    weeney
    -0.06
    什
    -0.06
    Reuters
    -0.06
    	func
    -0.06
    児
    -0.06
     اینکه
    -0.06
    /img
    -0.06
    Rightarrow
    -0.06
     Derm
    -0.06
    POSITIVE LOGITS
     Genuine
    0.06
     �
    0.06
    .positions
    0.06
    /{{$
    0.06
    _SENT
    0.06
     Про
    0.06
    "]))
    0.06
    หา
    0.06
     copp
    0.06
    0.06
    Act Density 0.006%

    No Known Activations