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

    Neuronpedia

    INDEX
    Explanations

    Jorge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     назнач
    -0.06
     edited
    -0.06
    mamız
    -0.06
    -keys
    -0.06
    Layout
    -0.06
    esát
    -0.05
    zew
    -0.05
    .getActive
    -0.05
    setUp
    -0.05
     През
    -0.05
    POSITIVE LOGITS
     Jorge
    0.08
    �
    0.07
    ama
    0.07
    žit
    0.07
    impact
    0.07
     componentName
    0.07
    -big
    0.06
    рос
    0.06
    즈
    0.06
     trận
    0.06
    Act Density 0.001%

    No Known Activations