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

    Neuronpedia

    INDEX
    Explanations

    Vu

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    abestanden
    -0.66
     Hartley
    -0.57
    ly
    -0.56
    IVEREF
    -0.56
    DOCTYPE
    -0.54
    jstor
    -0.53
     Vail
    -0.52
    ########.
    -0.50
    fxml
    -0.49
     Vali
    -0.48
    POSITIVE LOGITS
    oa̍t
    0.63
    ande
    0.60
    čenje
    0.55
     antig
    0.54
    andang
    0.54
    andi
    0.52
     UnityEditor
    0.52
    alga
    0.52
    antd
    0.51
    gend
    0.50
    Act Density 0.032%

    No Known Activations