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

    Neuronpedia

    INDEX
    Explanations

    has

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     inhibitors
    -0.06
    _DATABASE
    -0.06
     {//
    -0.06
    RDD
    -0.06
    RoleId
    -0.06
    _dataset
    -0.06
    �
    -0.06
    _DEPTH
    -0.06
    �
    -0.06
    iciency
    -0.06
    POSITIVE LOGITS
     Lol
    0.07
    :view
    0.07
    änder
    0.06
    领导
    0.06
    =this
    0.06
     exclude
    0.06
     reste
    0.06
     Mes
    0.06
    ensual
    0.06
    =json
    0.06
    Act Density 0.045%

    No Known Activations