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

    Neuronpedia

    INDEX
    Explanations

    Plus/minus signs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    euillez
    -0.07
    בוט
    -0.07
    อำนาจ
    -0.07
    _response
    -0.07
     Optical
    -0.07
    .api
    -0.07
    "));
↵
↵
    -0.06
    .Map
    -0.06
     Woo
    -0.06
    .mock
    -0.06
    POSITIVE LOGITS
    啸
    0.08
    皭
    0.07
     cheg
    0.07
    Adj
    0.07
     Jerome
    0.07
     extrad
    0.07
    ~~~~
    0.07
     belonged
    0.07
    甲状
    0.07
    oplan
    0.07
    Act Density 0.001%

    No Known Activations