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

    Neuronpedia

    INDEX
    Explanations

    mathematical/scientific papers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     descon
    -0.09
     Verify
    -0.08
     vanished
    -0.08
    |required
    -0.07
    過去
    -0.07
     produ
    -0.07
     exists
    -0.07
    提前
    -0.07
    	remove
    -0.07
    Filter
    -0.07
    POSITIVE LOGITS
     rept
    0.10
    천
    0.07
    AME
    0.07
    �
    0.07
     harm
    0.07
     Negative
    0.07
    Abort
    0.06
     stern
    0.06
     Gratuit
    0.06
    Campaign
    0.06
    Act Density 0.009%

    No Known Activations