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

    Neuronpedia

    INDEX
    Explanations

    Arial

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .place
    -0.07
     half
    -0.07
     chap
    -0.07
     rectangle
    -0.06
    R
    -0.06
    โทร
    -0.06
    	ref
    -0.06
    }$
    -0.06
     ante
    -0.06
     shop
    -0.06
    POSITIVE LOGITS
    :";
↵
    0.07
    并通过
    0.07
    عود
    0.07
     accountability
    0.07
     grievances
    0.07
     Bright
    0.07
    -original
    0.07
     ).↵↵
    0.07
     activity
    0.06
    𐰰
    0.06
    Act Density 0.001%

    No Known Activations