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

    Neuronpedia

    INDEX
    Explanations

    .read

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ($"{
    -0.07
     Bool
    -0.06
    为空
    -0.06
    (GET
    -0.06
     chod
    -0.06
     Ông
    -0.06
     Yaş
    -0.06
    posable
    -0.06
     ich
    -0.06
    _RESULT
    -0.06
    POSITIVE LOGITS
    .read
    0.28
    .write
    0.07
    .path
    0.07
    	Read
    0.07
     financ
    0.06
    	th
    0.06
     DJs
    0.06
     PARAMETERS
    0.06
    .ones
    0.06
     rejecting
    0.06
    Act Density 0.004%

    No Known Activations