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

    Neuronpedia

    INDEX
    Explanations

    Saving

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bull
    -0.06
     Dataset
    -0.06
    .Push
    -0.06
     política
    -0.06
     можлив
    -0.06
    	lbl
    -0.06
    _att
    -0.06
     Removed
    -0.06
    �
    -0.06
    ضان
    -0.06
    POSITIVE LOGITS
    amam
    0.07
     والأ
    0.06
     Const
    0.06
    ケース
    0.06
    hoff
    0.06
    жд
    0.06
     background
    0.06
     investigate
    0.06
     Constit
    0.06
     HR
    0.06
    Act Density 0.014%

    No Known Activations