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

    Neuronpedia

    INDEX
    Explanations

    arithmetic operations in code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Physical
    -0.07
    ,n
    -0.07
    räume
    -0.07
    ')}}↵
    -0.07
    '];?></
    -0.07
    	fs
    -0.07
    جار
    -0.07
    oston
    -0.06
    קא
    -0.06
     puss
    -0.06
    POSITIVE LOGITS
    扶持
    0.07
    akening
    0.07
    connection
    0.07
     cif
    0.07
    说服
    0.06
    切割
    0.06
     uplift
    0.06
    以下の
    0.06
    不清楚
    0.06
    非遗
    0.06
    Act Density 0.015%

    No Known Activations