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

    Neuronpedia

    INDEX
    Explanations

    hedge

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	elem
    -0.07
    session
    -0.06
     pronunciation
    -0.06
    超过
    -0.06
     keyboard
    -0.06
    Strings
    -0.05
     всего
    -0.05
     Ment
    -0.05
     distribution
    -0.05
     obstacle
    -0.05
    POSITIVE LOGITS
    indered
    0.08
     ASC
    0.07
    spiel
    0.07
    _FF
    0.07
     Lucy
    0.06
    918
    0.06
    ắm
    0.06
    xFD
    0.06
    -d
    0.06
    екту
    0.06
    Act Density 0.003%

    No Known Activations