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

    Neuronpedia

    INDEX
    Explanations

    self

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [to
    -0.07
     watts
    -0.06
    543
    -0.06
    zin
    -0.06
     cents
    -0.06
    侯
    -0.06
    ่วง
    -0.06
    -sized
    -0.06
     tonnes
    -0.06
    		    ↵
    -0.06
    POSITIVE LOGITS
     env
    0.07
    Iss
    0.07
     Applying
    0.06
    oliberal
    0.06
    _BACK
    0.06
    PC
    0.06
    istencia
    0.06
    ,port
    0.06
     mandatory
    0.06
    itos
    0.06
    Act Density 0.002%

    No Known Activations