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

    Neuronpedia

    INDEX
    Explanations

    Labeling

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     belongings
    -0.07
     TAR
    -0.07
     Hp
    -0.07
    Hp
    -0.06
    Civil
    -0.06
    oms
    -0.06
     timely
    -0.06
    Shopping
    -0.06
     Published
    -0.06
    	friend
    -0.06
    POSITIVE LOGITS
    ％
    0.07
     تهیه
    0.07
    ++;
    0.06
     những
    0.06
    acic
    0.06
    PLAY
    0.06
    /#
    0.06
     yılda
    0.06
     bếp
    0.06
     tipping
    0.06
    Act Density 0.009%

    No Known Activations