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

    Neuronpedia

    INDEX
    Explanations

    amic

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fundamentals
    -0.07
    Fault
    -0.07
    ****************
    -0.07
    Pwd
    -0.06
     currentValue
    -0.06
     を
    -0.06
    Jones
    -0.06
    而
    -0.06
    -solid
    -0.06
     Constructors
    -0.06
    POSITIVE LOGITS
     Гар
    0.07
     Tai
    0.07
     Aren
    0.06
    fit
    0.06
     shout
    0.06
    �璃
    0.06
    )(↵
    0.06
    _combo
    0.06
            
↵
    0.06
    ослав
    0.06
    Act Density 0.002%

    No Known Activations