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

    Neuronpedia

    INDEX
    Explanations

    who

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .BackColor
    -0.06
    .getObject
    -0.06
     existing
    -0.06
    	params
    -0.06
    参与
    -0.06
    _account
    -0.06
    .’”↵↵
    -0.06
    ifact
    -0.06
    STDOUT
    -0.05
     corr
    -0.05
    POSITIVE LOGITS
    etrics
    0.07
     Vader
    0.07
    [W
    0.06
     Jenna
    0.06
    Tyler
    0.06
    Ber
    0.06
     cần
    0.06
     Stephanie
    0.06
    终于
    0.06
     aston
    0.06
    Act Density 0.010%

    No Known Activations