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

    Neuronpedia

    INDEX
    Explanations

    cell

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Steering
    -0.07
    _Render
    -0.07
     Nexus
    -0.06
    igsaw
    -0.06
    RefCount
    -0.06
    listed
    -0.06
     swipe
    -0.06
    quiry
    -0.06
    ображ
    -0.06
     Evropské
    -0.06
    POSITIVE LOGITS
    .textField
    0.07
     SMALL
    0.06
    .metrics
    0.06
    asley
    0.06
    stit
    0.06
    .room
    0.06
     wound
    0.06
    压
    0.06
    (dirname
    0.06
     pretrained
    0.06
    Act Density 0.014%

    No Known Activations