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

    Neuronpedia

    INDEX
    Explanations

    coming out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     manager
    -0.07
    (sh
    -0.07
     función
    -0.06
     Recru
    -0.06
     politik
    -0.06
     dynasty
    -0.06
     translates
    -0.06
     Stable
    -0.06
     head
    -0.06
    條
    -0.06
    POSITIVE LOGITS
    noc
    0.07
     quasi
    0.07
     awareness
    0.06
     دولتی
    0.06
    	Route
    0.06
    无码
    0.06
     благ
    0.06
    _Il
    0.06
     columnName
    0.06
    .DeepEqual
    0.06
    Act Density 0.012%

    No Known Activations