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

    Neuronpedia

    INDEX
    Explanations

    Punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    凡是
    -0.07
     mama
    -0.07
    _issues
    -0.07
    OptionsItemSelected
    -0.06
    而又
    -0.06
    鹆
    -0.06
    的地方
    -0.06
    ornecedor
    -0.06
    [];
↵
    -0.06
    AffineTransform
    -0.06
    POSITIVE LOGITS
    ixmap
    0.08
    ony
    0.07
    phil
    0.07
     Jeremy
    0.07
    מניות
    0.07
    	table
    0.07
    Ins
    0.06
    ?</
    0.06
    กระท
    0.06
    	k
    0.06
    Act Density 0.048%

    No Known Activations